Four tools with basic descriptions and minimal parameter documentation. All tools are READ_ONLY and follow verb_noun naming (search_, get_, validate_, get_). However, descriptions are terse (10-20 chars), parameter descriptions lack detail on format/constraints, and output schemas are not documented in the source. No error handling guidance, no pagination support despite tools returning lists, and no tool annotations. The client code shows tools exist and are callable, but the server implementation details are not visible, tool definitions appear inferred from CLI usage rather than explicitly registered with full schemas.

• Expand tool descriptions to 50 - 200 characters. Example: 'search_gaps: Find unmet market needs and customer pain points in a specific domain. Returns ranked gaps with commercial intent scores. Use this to discover product opportunities before validate_idea.'
• Document output schemas explicitly. For search_gaps, specify: returns {gaps: [{id, title, url, commercialIntent, confidence}], total_count, next_cursor}. For validate_idea, specify: returns {verdict: {level, headline, detail}, matchCount}.
• Add min/max bounds to numeric parameters. E.g. 'limit: Maximum number of results (1 - 100, default 20)'. For 'query', add: 'Market or domain name (2 - 100 characters, e.g. "Shopify accounting").'
• Implement pagination for list-returning tools. Add 'offset' or 'cursor' parameter and return 'total_count' and 'next_cursor' in responses. Document in tool description: 'Supports pagination; call with cursor from previous response to fetch next page.'
• Add error recovery guidance. E.g. if validate_idea returns low confidence, suggest: 'Confidence is low. Try search_gaps to find stronger market signals, or refine your idea and retry.' If get_dossier fails due to missing API key, return: 'API key required. Set DDMARKETER_API_KEY environment variable.'