Two tools with basic descriptions but significant schema and parameter documentation gaps. 'analyze' and 'compare' have acceptable high-level descriptions (100+ chars), but input schemas lack proper type definitions for nested objects and arrays. Parameters lack detailed constraints, format specifications, and validation guidance. No output schemas documented. Error handling is minimal, no recovery guidance or actionable error messages. Tool names are verb-based but descriptions don't explain when to use each vs. the other. No evidence of idempotency guarantees or side-effect clarity.

• Add explicit JSON Schema type definitions: domain as 'string' with pattern/format (e.g., 'hostname or URL'), domains as 'array' with minItems: 2, items: {type: 'string'}.
• Document output schema for both tools. Specify that 'result' contains fields like: aiVisibilityScore (number 0-100), aiReadinessScore (number 0-100), platformVisibility (array of {platform, score}), strengths (array), gaps (array), recommendations (array).
• Replace generic error messages with actionable guidance. E.g., 'Invalid domain format. Expected: example.com or https://example.com' instead of 'Analysis failed'.
• Expand parameter descriptions with constraints. E.g., 'output: Optional file path (must be writable directory, .json extension). If omitted, results printed to stdout only.'
• Clarify tool selection in descriptions. Analyze: 'Deep analysis of a single domain's AI visibility across platforms.' Compare: 'Benchmark 2+ domains side-by-side to identify competitive gaps.'