Three tools with complete input schemas and descriptions, but descriptions are generic and lack LLM-optimized guidance. All parameters have types and descriptions, meeting baseline requirements. However, descriptions average ~60 chars (well below the 194-char production baseline) and lack context on WHEN to use each tool or dependencies between them. No output schemas documented. Error handling is absent from tool definitions. Parameters like 'freshness' lack enum constraints despite accepting only specific values (pd, pw, pm, py). No tool annotations (readOnlyHint, etc.) despite all being read-only operations.

• Expand tool descriptions to 100-200 chars. Example: 'Search the web using Brave Search API. Use this for general web queries, current events, and broad information discovery. Returns ranked results with titles, URLs, and snippets. Supports pagination via offset/count (max 20 per request).'
• Convert 'freshness' parameter to enum: {"type": "string", "enum": ["pd", "pw", "pm", "py"], "description": "Filter results by recency: pd=past day, pw=past week, pm=past month, py=past year. Omit for no filter."}
• Document output schema in tool description or separate schema field. Example: 'Returns {results: [{title, url, description, snippet}], total_count: number, next_offset: number}'
• Add readOnlyHint annotation to all three tools in tool registration to signal they are safe to cache and retry without side effects.
• Add error recovery guidance: 'If rate limited (429), wait 60 seconds before retrying. If query is invalid, simplify the search terms. If country/language unsupported, check Brave API docs for valid codes.'

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

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