Single tool 'readiness_scan' has a basic description (89 chars) and minimal schema. Input schema present but lacks detail: only 'target' parameter with generic string type and description. No output schema documented. No error handling guidance, no parameter constraints (e.g., file path validation, directory traversal protection), and no indication of what the JSON response structure contains. Tool name is verb-noun compliant but description does not explain WHEN to use it, WHAT the output fields mean, or HOW to interpret findings. Lacks production-grade rigor.

• Document the complete output schema: e.g., {"tool": string, "findings": [{"id": string, "sev": string, "where": string}], "score": number}. Include field descriptions and types.
• Expand tool description to 150-250 chars: explain that this scans YAML files for readiness gaps (TODO/FIXME/XXX markers), returns a C-rating-style score, and is useful for compliance/audit workflows.
• Add parameter constraints: 'target must be a valid local file or directory path (no parent directory traversal). Max depth: 10 levels. Supported formats: YAML, JSON.'
• Implement error handling with recovery hints: 'Path not found. Verify the file/directory exists and is readable.' 'Invalid YAML in {file}. Check syntax and retry.' 'Permission denied on {path}. Run with appropriate permissions.'
• Add tool annotation hints (readOnlyHint: true, idempotentHint: true) to signal to the LLM that this tool is safe to call repeatedly without side effects.