Two tools with basic schemas and descriptions, but significant gaps in parameter documentation and error handling. web_search has a reasonable description and schema with num_results constraint, but fetch_page lacks parameter description detail. Neither tool documents output schemas, error cases, or recovery guidance. No tool annotations (readOnlyHint/destructiveHint). Descriptions are adequate (50-100 chars) but lack context on when to use each tool or what they return. Parameter descriptions are minimal, 'Search query' and 'URL to fetch' do not explain format constraints, expected response structure, or failure modes.

• Document output schemas for both tools. Example: web_search returns {results: [{title, url, snippet, source}], total_count}; fetch_page returns {content, title, status_code, url}.
• Add parameter descriptions to fetch_page: 'url (string, required): Full HTTP/HTTPS URL to fetch. Must be valid and publicly accessible. Returns error if unreachable or rate-limited.'
• Add error handling guidance to tool descriptions: 'Returns error if query is empty, network timeout occurs, or rate limit is hit. Retry with exponential backoff for transient failures.'
• Add readOnlyHint=true to both tool definitions to signal they are safe, non-destructive operations that agents can call freely.
• Expand web_search description to explain when to use it vs fetch_page: 'Use for broad web searches. For specific URLs, use fetch_page. Returns up to 20 results; use pagination for more.'

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

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