Three tools with basic descriptions but critical gaps in schema documentation and parameter descriptions. list_docs and get_doc have empty input schemas ({}), violating the requirement that every parameter needs a description. search_docs has a single parameter with a description, but no output schemas are documented for any tool. Descriptions are present but generic (10-50 chars), below the 50-200 char baseline for LLM-optimized tools. No error handling guidance, no pagination support despite list_docs likely returning multiple items, and no indication of output structure.

• Add explicit input schemas to list_docs (e.g., limit: integer 1-100, offset: integer ≥0) and get_doc (e.g., name: string with pattern validation for relative paths). Document constraints in parameter descriptions.
• Document output schemas for all three tools. E.g., list_docs returns {documents: [{name: string, preview: string, size: integer}], total: integer}. get_doc returns {name: string, content: string}. search_docs returns {results: [{name: string, score: number, excerpt: string}]}.
• Expand descriptions to 80-150 chars. E.g., 'Lists all available documents with a preview of the first 90 characters. Call this first to discover available docs, or use search_docs to find specific content.' This guides LLM selection.
• Add pagination to list_docs: accept limit (default 20, max 100) and offset parameters. Return total count so agents know if more results exist. Cap results at 50 items per response.
• Add error handling: document that get_doc returns a clear error if the path doesn't exist (e.g., 'Document not found: test-docs/installation.md. Available documents: [list]. Did you mean test-docs/install.md?'). search_docs should handle empty queries gracefully.