Four tools with basic descriptions and minimal input schemas. All tools are READ_ONLY and well-named with action verbs (search_, list_, get_, read_). Descriptions are present but brief (10-80 chars), below the 50-200 char LLM-optimized baseline. Input schemas exist but lack depth: most parameters have only type and description, no enums, ranges, or validation constraints. No output schemas documented. Error handling and recovery guidance absent. Tool composition is reasonable (each does one thing), but parameter descriptions are sparse and do not explain constraints, formats, or dependencies.

• Document output schemas for all four tools. Example: search_wiki should return {results: [{slug: string, title: string, excerpt: string}], total: number, next_cursor?: string}. This enables LLMs to chain calls and extract IDs.
• Expand tool descriptions to 80-150 chars. Example: 'Search the wiki for pages by keyword. Returns up to 20 results with title, slug, and excerpt. Use read_wiki_page to fetch full content. Supports pagination via cursor.'
• Add constraint details to parameters. Example: query description should be 'Search query (1-200 chars, alphanumeric + spaces). Matches page titles and content.'
• Add pagination to list_review_cards: include limit (1-100, default 20) and offset/cursor parameters. Return total_count so LLMs know if more cards exist.
• Add error recovery hints. Example: 'If no results found, try a shorter query or check spelling. Call get_graph_insights to see available topics.'