Server has 5 tools with complete JSON schemas and descriptions. Naming follows verb_noun convention (web_search, fetch_page, save_note, list_notes, get_note). Descriptions are present but brief (avg 45 chars, below 194-char baseline). All parameters have type definitions and descriptions. However, output schemas are not documented, LLMs cannot predict response structure. Error handling exists but lacks recovery guidance. No tool annotations (readOnlyHint/destructiveHint). Parameter constraints are present (enums, defaults) but some descriptions lack format/range details.

• Document output schemas for all tools. Example: web_search returns [{title, url, snippet, source}], list_notes returns {notes: [{id, title, tags, created_at}], total, has_more}.
• Expand tool descriptions to 100-200 chars. Add WHEN to use: 'web_search: Find current information on the web. Use when you need recent data not in training data. Returns top 3-5 results by relevance.'
• Add tool annotations in server.ts. Mark save_note with destructiveHint=true, web_search/fetch_page/list_notes/get_note with readOnlyHint=true.
• Enhance error messages with recovery paths. E.g., 'Invalid note ID. Call list_notes() to find valid IDs.' instead of bare 'Invalid input'.
• Document pagination behavior in list_notes description: 'Returns paginated results (default limit=20). Use offset to fetch next page. Response includes total count.'

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry