Change two MCP descriptions to see if usage improves

[kendallgassner]

Changed

Updated two MCP tool descriptions to see if Copilot usage improves. Metrics indicate that the Primer MCP tools are not often used. Copilot seems to be struggling with understanding the tools purpose:

I cannot directly access https://primer.style/ or fetch live documentation from the internet. I rely on my training data and the code/documentation available in the repository. The Primer MCP tools would have been valuable for accessing up-to-date Primer documentation, especially for experimental components like Dialog. For future work, I should use those tools to ensure I'm following current best practices and using the latest API patterns.

Rollout strategy

• Patch release
• Minor release
• Major release; if selected, include a written rollout or migration plan
• None; if selected, include a brief description as to why

Testing & Reviewing

Merge checklist

• Added/updated tests
• Added/updated documentation
• Added/updated previews (Storybook)
• Changes are SSR compatible
• Tested in Chrome
• Tested in Firefox
• Tested in Safari
• Tested in Edge
• (GitHub staff only) Integration tests pass at github/github (Learn more about how to run integration tests)

[changeset-bot]

🦋 Changeset detected

Latest commit: cf6afc5

The changes in this PR will be included in the next version bump.

This PR includes changesets to release 1 package

Name	Type
@primer/mcp	Patch

Not sure what this means? Click here to learn what changesets are.

Click here if you're a maintainer who wants to add another changeset to this PR

[Copilot]

Pull Request Overview

Updates MCP tool descriptions to improve Copilot's understanding and usage of Primer React component documentation tools. The changes aim to address low usage metrics by making the tool purposes clearer and more discoverable.

• Expanded descriptions for get_component and get_component_accessibility_guidelines tools with detailed explanations
• Fixed error message references to use correct tool name list_components

[kendallgassner]

VRT failure seems unrelated.

[siddharthkp]

I don't understand this enough but I trust you with it

[siddharthkp]

VRT failure seems unrelated.

yeah, looks like a flaky test (0.01% change). Retrying the job

[kendallgassner]

The VRT tests are so flaky I keep getting bumped from the merge queue 😢 .

[JoseInTheArena]

@kendallgassner did usage improve?