Replace get_by_id with per-field MCP tools and improve docstrings #66
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
- Improve server-level instructions and all tool docstrings to clearly communicate hybrid search (by name and by meaning) with examples - Replace monolithic get_by_id tool with 6 focused per-field tools: get_source_code, get_source_link, get_docstring, get_description, get_module, get_dependencies - Each tool returns only id, name, and the requested field to reduce context pollution for AI agents - Add shared _execute_backend_get_by_id helper - Update search and search_summary docstrings to reference new tools - Replace TestGetByIdTool tests with 6 new test classes (30 tests)
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Outdated suggestions cannot be applied.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.
Summary
List.map,Nat.Prime) and semantic/natural language queries (e.g., "continuous function on a compact set")get_by_idtool with 6 focused per-field tools to reduce context pollution for AI agents:get_source_code— Lean source codeget_source_link— GitHub link to sourceget_docstring— documentation stringget_description— natural language informalizationget_module— module path in the packageget_dependencies— declarations this depends on{id, name, <field>}, so agents fetch exactly what they needsearch_summary→ per-field tools →searchonly when all fields neededTest plan