Server has 6 tools with basic schemas and descriptions, but significant gaps limit production readiness. All tools have input schemas with type definitions and descriptions present, meeting minimum requirements. However, descriptions are generic (avg ~60 chars, well below the 194-char baseline for A+ tools), lack context about when to use each tool, and omit prerequisites or dependencies. Output schemas are undocumented, LLMs cannot predict return structure. Error handling returns raw error messages without recovery guidance. No tool annotations (readOnlyHint/destructiveHint) despite clear risk distinctions (3 WRITE, 3 READ_ONLY). Parameter descriptions lack format constraints, ranges, or validation rules. No pagination support despite tools returning lists (query-notion-database, get-github-repos). Tool composition is reasonable but lacks chaining metadata.

• Add output schemas to all tools. Document return type, fields, and structure. E.g., get-weather should return {temperature: number, condition: string, location: string} so LLMs know what to extract.
• Expand descriptions to 100-200 chars. Include WHEN to use the tool, WHAT it returns, and any prerequisites. E.g., 'Retrieve a Notion page by ID. Returns page title and metadata. Use after searching for a page ID via query-notion-database.'
• Add tool annotations: mark create-notion-page and create-github-issue with destructiveHint=true; mark read-only tools with readOnlyHint=true. This enables agents to reason about retry safety and side effects.
• Improve error messages with recovery guidance. E.g., 'City not found. Try search_cities() with a partial name, or check spelling.' Return available alternatives when possible.
• Add pagination to query-notion-database and get-github-repos. Include limit (default 20, max 100) and offset/cursor parameters. Return total_count so agents know if more results exist.