perf: MCP optimize tokens use #3307
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Added logic to extract short command descriptions from the README.md command table for SkillDefinition. Falls back to the first sentence of the USAGE text if not found. Includes a cleaning function to remove markdown links, HTML tags, and certain emojis from the extracted description.
Expanded the 'select' command guidance to include regex and special character usage. Improved the enhanceDescription function to append contextual hints, common patterns, error prevention, and help instructions for each tool, making it easier for users to select and use the correct qsv command. Updated the generic qsv_command tool description to mention the help option.
Shorten and clarify qsv skill descriptions. Updated the descriptions in multiple qsv skill JSON files to be more concise and focused, removing excessive detail and examples. This improves readability and consistency across the skill definitions.
Contributor
There was a problem hiding this comment.
Pull request overview
This pull request optimizes token usage for MCP (Model Context Protocol) tools by replacing verbose descriptions with concise ones extracted from the README.md command table. The change aims to reduce the token count sent to LLMs while preserving essential information, with additional contextual guidance added through the TypeScript layer.
Changes:
- Added new Rust functions to extract and clean short descriptions from README.md command table
- Updated description generation logic to prefer concise README descriptions over verbose USAGE text
- Enhanced TypeScript tool descriptions with structured guidance hints for better tool selection
- Updated 50+ JSON skill files with concise descriptions optimized for token efficiency
Reviewed changes
Copilot reviewed 67 out of 67 changed files in this pull request and generated 8 comments.
| File | Description |
|---|---|
| src/mcp_skills_gen.rs | Added extract_short_description_from_readme and clean_readme_description functions to extract concise descriptions from README table; updated parse method to use README descriptions as primary source with fallback to USAGE text |
| .claude/skills/src/mcp-tools.ts | Enhanced select command guidance to include regex selector syntax; added documentation comments explaining the concise description strategy and reference to qsv_help tool |
| .claude/skills/qsv/*.json | Updated 50+ skill definition files with concise descriptions extracted from README, replacing verbose USAGE-based descriptions |
[skip ci]
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
No description provided.