Four tools with clear verb-noun naming (wikipedia_search, wikipedia_get_page, wikipedia_get_summary, wikipedia_random) and basic descriptions. All tools have input schemas with type definitions and parameter descriptions. However, descriptions are minimal (10-50 chars), falling below the 50-200 char baseline for LLM-optimized docs. No output schemas documented. Parameter descriptions lack format/constraint details (e.g., 'limit' accepts 1-50 but description doesn't specify range). No error recovery guidance. All tools are READ_ONLY, which is good, but descriptions don't explicitly state this or explain when to use each tool vs. alternatives.

• Expand tool descriptions to 50-200 chars. Example: 'Search Wikipedia articles by query. Returns up to 50 results with title and snippet. Use this to discover articles; then call wikipedia_get_summary or wikipedia_get_page to read full content.'
• Document output schemas for each tool. Specify that wikipedia_search returns {title, snippet, url}, wikipedia_get_page returns {title, content, url}, etc.
• Add min/max constraints to numeric parameters in the schema. For 'limit', set minimum: 1, maximum: 50 in the JSON Schema definition.
• Enhance error messages with recovery guidance. E.g., 'Article not found. Try wikipedia_search() with a partial title or different keywords.'
• Add a tool annotation or note clarifying that wikipedia_get_page returns full content (potentially large) while wikipedia_get_summary returns a brief extract. Help LLMs choose based on context window and use case.

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

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