diff --git a/docs/cli_reference.md b/docs/cli_reference.md
index 20c06029..d3e403b7 100644
--- a/docs/cli_reference.md
+++ b/docs/cli_reference.md
@@ -1,252 +1,882 @@
 # CLI Reference
 
-You may use the `llama-stack-client` to query information about the distribution.
+Welcome to the llama-stack-client CLI - a command-line interface for interacting with Llama Stack
 
-#### `llama-stack-client`
-```bash
-$ llama-stack-client -h
+```
+Usage: llama-stack-client [OPTIONS] COMMAND [ARGS]...
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--version**: Show the version and exit. [default: False]
+
+* **--endpoint**: Llama Stack distribution endpoint [default: ]
+
+* **--api-key**: Llama Stack distribution API key [default: ]
+
+* **--config**: Path to config file
+
+**Commands**
+
+* **configure**: Configure Llama Stack Client CLI.
+
+* **datasets**: Manage datasets.
+
+* **eval**: Run evaluation tasks.
+
+* **eval_tasks**: Manage evaluation tasks.
+
+* **inference**: Inference (chat).
 
-usage: llama-stack-client [-h] {models,memory_banks,shields} ...
+* **inspect**: Inspect server configuration.
 
-Welcome to the LlamaStackClient CLI
+* **models**: Manage GenAI models.
 
-options:
-  -h, --help            show this help message and exit
+* **post_training**: Post-training.
+
+* **providers**: Manage API providers.
+
+* **scoring_functions**: Manage scoring functions.
+
+* **shields**: Manage safety shield services.
+
+* **toolgroups**: Manage available tool groups.
+
+* **vector_dbs**: Manage vector databases.
+
+
+
+## configure
+
+Configure Llama Stack Client CLI.
 
-subcommands:
-  {models,memory_banks,shields}
 ```
+Usage: llama-stack-client configure [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--endpoint**: Llama Stack distribution endpoint [default: ]
+
+* **--api-key**: Llama Stack distribution API key [default: ]
+
+
+
+## datasets
+
+Manage datasets.
 
-#### `llama-stack-client configure`
-```bash
-$ llama-stack-client configure
-> Enter the host name of the Llama Stack distribution server: localhost
-> Enter the port number of the Llama Stack distribution server: 5000
-Done! You can now use the Llama Stack Client CLI with endpoint http://localhost:5000
 ```
+Usage: llama-stack-client datasets [OPTIONS] COMMAND [ARGS]...
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
 
+**Commands**
 
-#### `llama-stack-client providers list`
-```bash
-$ llama-stack-client providers list
+* **list**: Show available datasets on distribution...
+
+* **register**: Create a new dataset
+
+
+
+### list
+
+Show available datasets on distribution endpoint
+
+```
+Usage: llama-stack-client datasets list [OPTIONS]
 ```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+### register
+
+Create a new dataset
+
 ```
-+-----------+----------------+-----------------+
-| API       | Provider ID    | Provider Type   |
-+===========+================+=================+
-| scoring   | meta0          | meta-reference  |
-+-----------+----------------+-----------------+
-| datasetio | meta0          | meta-reference  |
-+-----------+----------------+-----------------+
-| inference | tgi0           | remote::tgi     |
-+-----------+----------------+-----------------+
-| memory    | meta-reference | meta-reference  |
-+-----------+----------------+-----------------+
-| agents    | meta-reference | meta-reference  |
-+-----------+----------------+-----------------+
-| telemetry | meta-reference | meta-reference  |
-+-----------+----------------+-----------------+
-| safety    | meta-reference | meta-reference  |
-+-----------+----------------+-----------------+
+Usage: llama-stack-client datasets register [OPTIONS]
 ```
 
-#### `llama-stack-client models list`
-```bash
-$ llama-stack-client models list
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--dataset-id**: Id of the dataset
+
+* **--provider-id**: Provider ID for the dataset
+
+* **--provider-dataset-id**: Provider's dataset ID
+
+* **--metadata**: Metadata of the dataset
+
+* **--url**: URL of the dataset
+
+* **--dataset-path**: Local file path to the dataset. If specified, upload dataset via URL
+
+* **--schema**: JSON schema of the dataset
+
+
+
+## eval
+
+Run evaluation tasks.
+
+```
+Usage: llama-stack-client eval [OPTIONS] COMMAND [ARGS]...
 ```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **run-benchmark**: Run a evaluation benchmark task
+
+* **run-scoring**: Run scoring from application datasets
+
+
+
+### run-benchmark
+
+Run a evaluation benchmark task
+
 ```
-+----------------------+----------------------+---------------+----------------------------------------------------------+
-| identifier           | llama_model          | provider_id   | metadata                                                 |
-+======================+======================+===============+==========================================================+
-| Llama3.1-8B-Instruct | Llama3.1-8B-Instruct | tgi0          | {'huggingface_repo': 'meta-llama/Llama-3.1-8B-Instruct'} |
-+----------------------+----------------------+---------------+----------------------------------------------------------+
+Usage: llama-stack-client eval run-benchmark [OPTIONS] BENCHMARK_IDS...
 ```
 
-#### `llama-stack-client models get`
-```bash
-$ llama-stack-client models get Llama3.1-8B-Instruct
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--model-id**: model id to run the benchmark eval on
+
+* **--output-dir**: Path to the dump eval results output directory
+
+* **--num-examples**: Number of examples to evaluate on, useful for debugging
+
+* **--temperature**: temperature in the sampling params to run generation [default: 0.0]
+
+* **--max-tokens**: max-tokens in the sampling params to run generation [default: 4096]
+
+* **--top-p**: top-p in the sampling params to run generation [default: 0.9]
+
+* **--repeat-penalty**: repeat-penalty in the sampling params to run generation [default: 1.0]
+
+* **--visualize**: Visualize evaluation results after completion [default: False]
+
+**Arguments**
+
+* **BENCHMARK_IDS**
+
+
+
+### run-scoring
+
+Run scoring from application datasets
+
+```
+Usage: llama-stack-client eval run-scoring [OPTIONS] SCORING_FUNCTION_IDS...
 ```
 
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--dataset-id**: Pre-registered dataset_id to score (from llama-stack-client datasets list)
+
+* **--dataset-path**: Path to the dataset file to score
+
+* **--scoring-params-config**: Path to the scoring params config file in JSON format
+
+* **--num-examples**: Number of examples to evaluate on, useful for debugging
+
+* **--output-dir**: Path to the dump eval results output directory
+
+* **--visualize**: Visualize evaluation results after completion [default: False]
+
+**Arguments**
+
+* **SCORING_FUNCTION_IDS**
+
+
+
+## eval-tasks
+
+Manage evaluation tasks.
+
 ```
-+----------------------+----------------------+----------------------------------------------------------+---------------+
-| identifier           | llama_model          | metadata                                                 | provider_id   |
-+======================+======================+==========================================================+===============+
-| Llama3.1-8B-Instruct | Llama3.1-8B-Instruct | {'huggingface_repo': 'meta-llama/Llama-3.1-8B-Instruct'} | tgi0          |
-+----------------------+----------------------+----------------------------------------------------------+---------------+
+Usage: llama-stack-client eval-tasks [OPTIONS] COMMAND [ARGS]...
 ```
 
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
 
-```bash
-$ llama-stack-client models get Random-Model
+**Commands**
 
-Model RandomModel is not found at distribution endpoint host:port. Please ensure endpoint is serving specified model.
+* **list**: Show available eval tasks on distribution...
+
+* **register**: Register a new eval task
+
+
+
+### list
+
+Show available eval tasks on distribution endpoint
+
+```
+Usage: llama-stack-client eval-tasks list [OPTIONS]
 ```
 
-#### `llama-stack-client models register`
+**Options**
 
-```bash
-$ llama-stack-client models register <model_id> [--provider-id <provider_id>] [--provider-model-id <provider_model_id>] [--metadata <metadata>]
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+### register
+
+Register a new eval task
+
+```
+Usage: llama-stack-client eval-tasks register [OPTIONS]
 ```
 
-#### `llama-stack-client models update`
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--eval-task-id**: ID of the eval task
+
+* **--dataset-id**: ID of the dataset to evaluate
+
+* **--scoring-functions**: Scoring functions to use for evaluation
+
+* **--provider-id**: Provider ID for the eval task
+
+* **--provider-eval-task-id**: Provider's eval task ID
+
+* **--metadata**: Metadata for the eval task in JSON format
+
 
-```bash
-$ llama-stack-client models update <model_id> [--provider-id <provider_id>] [--provider-model-id <provider_model_id>] [--metadata <metadata>]
+
+## inference
+
+Inference (chat).
+
+```
+Usage: llama-stack-client inference [OPTIONS] COMMAND [ARGS]...
 ```
 
-#### `llama-stack-client models delete`
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **chat-completion**: Show available inference chat completion...
+
+
+
+### chat-completion
+
+Show available inference chat completion endpoints on distribution endpoint
 
-```bash
-$ llama-stack-client models delete <model_id>
 ```
+Usage: llama-stack-client inference chat-completion [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
 
-#### `llama-stack-client vector_dbs list`
-```bash
-$ llama-stack-client vector_dbs list
+* **--message**: Message
+
+* **--stream**: Streaming [default: False]
+
+* **--session**: Start a Chat Session [default: False]
+
+* **--model-id**: Model ID
+
+
+
+## inspect
+
+Inspect server configuration.
+
+```
+Usage: llama-stack-client inspect [OPTIONS] COMMAND [ARGS]...
 ```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **version**: Show available providers on distribution...
+
+
+
+### version
+
+Show available providers on distribution endpoint
+
 ```
-+--------------+----------------+---------------------+---------------+------------------------+
-| identifier   | provider_id    | provider_resource_id| vector_db_type| params                |
-+==============+================+=====================+===============+========================+
-| test_bank    | meta-reference | test_bank          | vector        | embedding_model: all-MiniLM-L6-v2
-                                                                      embedding_dimension: 384|
-+--------------+----------------+---------------------+---------------+------------------------+
+Usage: llama-stack-client inspect version [OPTIONS]
 ```
 
-#### `llama-stack-client vector_dbs register`
-```bash
-$ llama-stack-client vector_dbs register <vector-db-id> [--provider-id <provider-id>] [--provider-vector-db-id <provider-vector-db-id>] [--embedding-model <embedding-model>] [--embedding-dimension <embedding-dimension>]
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+## models
+
+Manage GenAI models.
+
+```
+Usage: llama-stack-client models [OPTIONS] COMMAND [ARGS]...
 ```
 
-Options:
-- `--provider-id`: Optional. Provider ID for the vector db
-- `--provider-vector-db-id`: Optional. Provider's vector db ID
-- `--embedding-model`: Optional. Embedding model to use. Default: "all-MiniLM-L6-v2"
-- `--embedding-dimension`: Optional. Dimension of embeddings. Default: 384
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **get**: Show available llama models at distribution...
+
+* **list**: Show available llama models at distribution...
+
+* **register**: Register a new model at distribution endpoint
+
+* **unregister**: Unregister a model from distribution endpoint
+
+
+
+### get
+
+Show available llama models at distribution endpoint
 
-#### `llama-stack-client vector_dbs unregister`
-```bash
-$ llama-stack-client vector_dbs unregister <vector-db-id>
 ```
+Usage: llama-stack-client models get [OPTIONS] MODEL_ID
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Arguments**
+
+* **MODEL_ID**
+
+
+
+### list
+
+Show available llama models at distribution endpoint
 
-#### `llama-stack-client shields list`
-```bash
-$ llama-stack-client shields list
 ```
+Usage: llama-stack-client models list [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+### register
+
+Register a new model at distribution endpoint
 
 ```
-+--------------+----------+----------------+-------------+
-| identifier   | params   | provider_id    | type        |
-+==============+==========+================+=============+
-| llama_guard  | {}       | meta-reference | llama_guard |
-+--------------+----------+----------------+-------------+
+Usage: llama-stack-client models register [OPTIONS] MODEL_ID
 ```
 
-#### `llama-stack-client shields register`
-```bash
-$ llama-stack-client shields register --shield-id <shield-id> [--provider-id <provider-id>] [--provider-shield-id <provider-shield-id>] [--params <params>]
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--provider-id**: Provider ID for the model
+
+* **--provider-model-id**: Provider's model ID
+
+* **--metadata**: JSON metadata for the model
+
+**Arguments**
+
+* **MODEL_ID**
+
+
+
+### unregister
+
+Unregister a model from distribution endpoint
+
+```
+Usage: llama-stack-client models unregister [OPTIONS] MODEL_ID
 ```
 
-Options:
-- `--shield-id`: Required. ID of the shield
-- `--provider-id`: Optional. Provider ID for the shield
-- `--provider-shield-id`: Optional. Provider's shield ID
-- `--params`: Optional. JSON configuration parameters for the shield
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Arguments**
+
+* **MODEL_ID**
+
+
+
+## post-training
+
+Post-training.
 
-#### `llama-stack-client eval_tasks list`
-```bash
-$ llama-stack-client eval_tasks list
 ```
+Usage: llama-stack-client post-training [OPTIONS] COMMAND [ARGS]...
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **artifacts**: Get the training artifacts of a specific post...
+
+* **cancel**: Cancel the training job
+
+* **list**: Show the list of available post training jobs
 
-#### `llama-stack-client eval_tasks register`
-```bash
-$ llama-stack-client eval_tasks register --eval-task-id <eval-task-id> --dataset-id <dataset-id> --scoring-functions <function1> [<function2> ...] [--provider-id <provider-id>] [--provider-eval-task-id <provider-eval-task-id>] [--metadata <metadata>]
+* **status**: Show the status of a specific post training...
+
+* **supervised_fine_tune**: Kick off a supervised fine tune job
+
+
+
+### artifacts
+
+Get the training artifacts of a specific post training job
+
+```
+Usage: llama-stack-client post-training artifacts [OPTIONS]
 ```
 
-Options:
-- `--eval-task-id`: Required. ID of the eval task
-- `--dataset-id`: Required. ID of the dataset to evaluate
-- `--scoring-functions`: Required. One or more scoring functions to use for evaluation
-- `--provider-id`: Optional. Provider ID for the eval task
-- `--provider-eval-task-id`: Optional. Provider's eval task ID
-- `--metadata`: Optional. Metadata for the eval task in JSON format
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--job-uuid**: Job UUID
+
+
+
+### cancel
+
+Cancel the training job
+
+```
+Usage: llama-stack-client post-training cancel [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--job-uuid**: Job UUID
+
+
+
+### list
+
+Show the list of available post training jobs
+
+```
+Usage: llama-stack-client post-training list [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+### status
+
+Show the status of a specific post training job
+
+```
+Usage: llama-stack-client post-training status [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--job-uuid**: Job UUID
+
+
+
+### supervised_fine_tune
+
+Kick off a supervised fine tune job
+
+```
+Usage: llama-stack-client post-training supervised_fine_tune 
+           [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--job-uuid**: Job UUID
+
+* **--model**: Model ID
+
+* **--algorithm-config**: Algorithm Config
+
+* **--training-config**: Training Config
+
+* **--checkpoint-dir**: Checkpoint Config
+
+
+
+## providers
+
+Manage API providers.
 
-#### `llama-stack-client eval run-benchmark`
-```bash
-$ llama-stack-client eval run-benchmark <eval-task-id1> [<eval-task-id2> ...] --eval-task-config <config-file> --output-dir <output-dir> [--num-examples <num>] [--visualize]
 ```
+Usage: llama-stack-client providers [OPTIONS] COMMAND [ARGS]...
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **list**: Show available providers on distribution...
+
+
 
-Options:
-- `--eval-task-config`: Required. Path to the eval task config file in JSON format
-- `--output-dir`: Required. Path to the directory where evaluation results will be saved
-- `--num-examples`: Optional. Number of examples to evaluate (useful for debugging)
-- `--visualize`: Optional flag. If set, visualizes evaluation results after completion
+### list
 
-Example eval_benchmark_config.json:
-```json
-{
-    "type": "benchmark",
-    "eval_candidate": {
-        "type": "model",
-        "model": "Llama3.1-405B-Instruct",
-        "sampling_params": {
-            "strategy": "greedy",
-            "temperature": 0,
-            "top_p": 0.95,
-            "top_k": 0,
-            "max_tokens": 0,
-            "repetition_penalty": 1.0
-        }
-    }
-}
+Show available providers on distribution endpoint
+
+```
+Usage: llama-stack-client providers list [OPTIONS]
 ```
 
-#### `llama-stack-client eval run-scoring`
-```bash
-$ llama-stack-client eval run-scoring <eval-task-id> --eval-task-config <config-file> --output-dir <output-dir> [--num-examples <num>] [--visualize]
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+## scoring-functions
+
+Manage scoring functions.
+
+```
+Usage: llama-stack-client scoring-functions [OPTIONS] COMMAND [ARGS]...
 ```
 
-Options:
-- `--eval-task-config`: Required. Path to the eval task config file in JSON format
-- `--output-dir`: Required. Path to the directory where scoring results will be saved
-- `--num-examples`: Optional. Number of examples to evaluate (useful for debugging)
-- `--visualize`: Optional flag. If set, visualizes scoring results after completion
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **list**: Show available scoring functions on...
+
+* **register**: Register a new scoring function
+
 
-#### `llama-stack-client toolgroups list`
-```bash
-$ llama-stack-client toolgroups list
+
+### list
+
+Show available scoring functions on distribution endpoint
+
+```
+Usage: llama-stack-client scoring-functions list [OPTIONS]
 ```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+### register
+
+Register a new scoring function
+
 ```
-+---------------------------+------------------+------+---------------+
-| identifier                | provider_id      | args | mcp_endpoint  |
-+===========================+==================+======+===============+
-| builtin::code_interpreter | code-interpreter | None | None         |
-+---------------------------+------------------+------+---------------+
-| builtin::rag             | rag-runtime      | None | None         |
-+---------------------------+------------------+------+---------------+
-| builtin::websearch       | tavily-search    | None | None         |
-+---------------------------+------------------+------+---------------+
+Usage: llama-stack-client scoring-functions register [OPTIONS]
 ```
 
-#### `llama-stack-client toolgroups get`
-```bash
-$ llama-stack-client toolgroups get <toolgroup_id>
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--scoring-fn-id**: Id of the scoring function
+
+* **--description**: Description of the scoring function
+
+* **--return-type**: Return type of the scoring function
+
+* **--provider-id**: Provider ID for the scoring function
+
+* **--provider-scoring-fn-id**: Provider's scoring function ID
+
+* **--params**: Parameters for the scoring function in JSON format
+
+
+
+## shields
+
+Manage safety shield services.
+
 ```
+Usage: llama-stack-client shields [OPTIONS] COMMAND [ARGS]...
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **list**: Show available safety shields on distribution...
 
-Shows detailed information about a specific toolgroup. If the toolgroup is not found, displays an error message.
+* **register**: Register a new safety shield
+
+
+
+### list
+
+Show available safety shields on distribution endpoint
 
-#### `llama-stack-client toolgroups register`
-```bash
-$ llama-stack-client toolgroups register <toolgroup_id> [--provider-id <provider-id>] [--provider-toolgroup-id <provider-toolgroup-id>] [--mcp-config <mcp-config>] [--args <args>]
 ```
+Usage: llama-stack-client shields list [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
 
-Options:
-- `--provider-id`: Optional. Provider ID for the toolgroup
-- `--provider-toolgroup-id`: Optional. Provider's toolgroup ID
-- `--mcp-config`: Optional. JSON configuration for the MCP endpoint
-- `--args`: Optional. JSON arguments for the toolgroup
 
-#### `llama-stack-client toolgroups unregister`
-```bash
-$ llama-stack-client toolgroups unregister <toolgroup_id>
+
+### register
+
+Register a new safety shield
+
+```
+Usage: llama-stack-client shields register [OPTIONS]
 ```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--shield-id**: Id of the shield
+
+* **--provider-id**: Provider ID for the shield
+
+* **--provider-shield-id**: Provider's shield ID
+
+* **--params**: JSON configuration parameters for the shield
+
+
+
+## toolgroups
+
+Manage available tool groups.
+
+```
+Usage: llama-stack-client toolgroups [OPTIONS] COMMAND [ARGS]...
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **get**: Show available llama toolgroups at...
+
+* **list**: Show available llama toolgroups at...
+
+* **register**: Register a new toolgroup at distribution...
+
+* **unregister**: Unregister a toolgroup from distribution...
+
+
+
+### get
+
+Show available llama toolgroups at distribution endpoint
+
+```
+Usage: llama-stack-client toolgroups get [OPTIONS] TOOLGROUP_ID
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Arguments**
+
+* **TOOLGROUP_ID**
+
+
+
+### list
+
+Show available llama toolgroups at distribution endpoint
+
+```
+Usage: llama-stack-client toolgroups list [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+### register
+
+Register a new toolgroup at distribution endpoint
+
+```
+Usage: llama-stack-client toolgroups register [OPTIONS] TOOLGROUP_ID
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--provider-id**: Provider ID for the toolgroup
+
+* **--provider-toolgroup-id**: Provider's toolgroup ID
+
+* **--mcp-config**: JSON mcp_config for the toolgroup
+
+* **--args**: JSON args for the toolgroup
+
+**Arguments**
+
+* **TOOLGROUP_ID**
+
+
+
+### unregister
+
+Unregister a toolgroup from distribution endpoint
+
+```
+Usage: llama-stack-client toolgroups unregister [OPTIONS] TOOLGROUP_ID
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Arguments**
+
+* **TOOLGROUP_ID**
+
+
+
+## vector-dbs
+
+Manage vector databases.
+
+```
+Usage: llama-stack-client vector-dbs [OPTIONS] COMMAND [ARGS]...
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Commands**
+
+* **list**: Show available vector dbs on distribution...
+
+* **register**: Create a new vector db
+
+* **unregister**: Delete a vector db
+
+
+
+### list
+
+Show available vector dbs on distribution endpoint
+
+```
+Usage: llama-stack-client vector-dbs list [OPTIONS]
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+
+
+### register
+
+Create a new vector db
+
+```
+Usage: llama-stack-client vector-dbs register [OPTIONS] VECTOR_DB_ID
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+* **--provider-id**: Provider ID for the vector db
+
+* **--provider-vector-db-id**: Provider's vector db ID
+
+* **--embedding-model**: Embedding model (for vector type) [default: all-MiniLM-L6-v2]
+
+* **--embedding-dimension**: Embedding dimension (for vector type) [default: 384]
+
+**Arguments**
+
+* **VECTOR_DB_ID**
+
+
+
+### unregister
+
+Delete a vector db
+
+```
+Usage: llama-stack-client vector-dbs unregister [OPTIONS] VECTOR_DB_ID
+```
+
+**Options**
+
+* **-h, --help**: Show this message and exit. [default: False]
+
+**Arguments**
+
+* **VECTOR_DB_ID**
diff --git a/scripts/gen_cli_doc.py b/scripts/gen_cli_doc.py
new file mode 100644
index 00000000..859b88d2
--- /dev/null
+++ b/scripts/gen_cli_doc.py
@@ -0,0 +1,82 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+import os
+from pathlib import Path
+
+import click
+from llama_stack_client.lib.cli.llama_stack_client import llama_stack_client
+
+
+def generate_markdown_docs(command, parent=None, level=1):
+    """Generate markdown documentation for a click command."""
+    ctx = click.Context(command, info_name=command.name, parent=parent)
+
+    # Start with the command name as a header
+    prefix = "#" * level
+    if level == 1:
+        doc = [f"{prefix} CLI Reference\n"]
+    else:
+        doc = [f"{prefix} {command.name}\n"]
+
+    # Add command help docstring
+    if command.help:
+        doc.append(f"{command.help}\n")
+
+    # Add usage
+    doc.append(f"```\n{command.get_usage(ctx)}\n```\n")
+
+    # Add options if present
+    has_options = False
+    for param in command.get_params(ctx):
+        if isinstance(param, click.Option):
+            if not has_options:
+                doc.append("**Options**\n")
+                has_options = True
+            opts = ", ".join(param.opts)
+            help_text = param.help or ""
+            default = f" [default: {param.default}]" if param.default is not None else ""
+            doc.append(f"* **{opts}**: {help_text}{default}\n")
+
+    # Add arguments if present
+    has_arguments = False
+    for param in command.get_params(ctx):
+        if isinstance(param, click.Argument):
+            if not has_arguments:
+                doc.append("**Arguments**\n")
+                has_arguments = True
+            name = param.name.upper()
+            doc.append(f"* **{name}**\n")
+
+    # If this is a group with commands, add subcommands
+    if isinstance(command, click.Group):
+        doc.append("**Commands**\n")
+        for cmd_name in command.list_commands(ctx):
+            cmd = command.get_command(ctx, cmd_name)
+            cmd_help = cmd.get_short_help_str() if cmd else ""
+            doc.append(f"* **{cmd_name}**: {cmd_help}\n")
+
+        # Add detailed subcommand documentation
+        for cmd_name in command.list_commands(ctx):
+            cmd = command.get_command(ctx, cmd_name)
+            if cmd:
+                doc.append("\n")
+                doc.extend(generate_markdown_docs(cmd, ctx, level + 1))
+
+    return doc
+
+
+if __name__ == "__main__":
+    # Generate the docs
+    markdown_lines = generate_markdown_docs(llama_stack_client)
+    markdown = "\n".join(markdown_lines)
+
+    # Write to file
+    file_path = Path(__file__).parent.parent / "docs" / "cli_reference.md"
+    with open(file_path, "w") as f:
+        f.write(markdown)
+
+    print(f"Documentation generated in {file_path}")
diff --git a/src/llama_stack_client/lib/cli/llama_stack_client.py b/src/llama_stack_client/lib/cli/llama_stack_client.py
index d2b86528..54c46aaa 100644
--- a/src/llama_stack_client/lib/cli/llama_stack_client.py
+++ b/src/llama_stack_client/lib/cli/llama_stack_client.py
@@ -35,8 +35,8 @@
 @click.option("--api-key", type=str, help="Llama Stack distribution API key", default="")
 @click.option("--config", type=str, help="Path to config file", default=None)
 @click.pass_context
-def cli(ctx, endpoint: str, api_key: str, config: str | None):
-    """Welcome to the LlamaStackClient CLI"""
+def llama_stack_client(ctx, endpoint: str, api_key: str, config: str | None):
+    """Welcome to the llama-stack-client CLI - a command-line interface for interacting with Llama Stack"""
     ctx.ensure_object(dict)
 
     # If no config provided, check default location
@@ -80,23 +80,23 @@ def cli(ctx, endpoint: str, api_key: str, config: str | None):
 
 
 # Register all subcommands
-cli.add_command(models, "models")
-cli.add_command(vector_dbs, "vector_dbs")
-cli.add_command(shields, "shields")
-cli.add_command(eval_tasks, "eval_tasks")
-cli.add_command(providers, "providers")
-cli.add_command(datasets, "datasets")
-cli.add_command(configure, "configure")
-cli.add_command(scoring_functions, "scoring_functions")
-cli.add_command(eval, "eval")
-cli.add_command(inference, "inference")
-cli.add_command(post_training, "post_training")
-cli.add_command(inspect, "inspect")
-cli.add_command(toolgroups, "toolgroups")
+llama_stack_client.add_command(models, "models")
+llama_stack_client.add_command(vector_dbs, "vector_dbs")
+llama_stack_client.add_command(shields, "shields")
+llama_stack_client.add_command(eval_tasks, "eval_tasks")
+llama_stack_client.add_command(providers, "providers")
+llama_stack_client.add_command(datasets, "datasets")
+llama_stack_client.add_command(configure, "configure")
+llama_stack_client.add_command(scoring_functions, "scoring_functions")
+llama_stack_client.add_command(eval, "eval")
+llama_stack_client.add_command(inference, "inference")
+llama_stack_client.add_command(post_training, "post_training")
+llama_stack_client.add_command(inspect, "inspect")
+llama_stack_client.add_command(toolgroups, "toolgroups")
 
 
 def main():
-    cli()
+    llama_stack_client()
 
 
 if __name__ == "__main__":