Single tool 'memorybank_scan' has a basic description (71 chars) but lacks critical detail on when/why to use it. Input schema is minimal: only 'target' (string) with a 72-char description. No output schema documented. No error handling guidance, no parameter constraints (e.g., path validation, max depth), and no indication of side effects or prerequisites. The tool name uses verb_noun pattern correctly, but the description does not explain what 'memory markers' are, what findings are returned, or how to interpret the JSON. Baseline: A+ tools average 194 chars in description and 72 chars per param; this tool meets param length but falls short on description depth and output documentation.

• Expand description to 150 - 250 chars: 'Scans a directory tree for code markers (TODO, FIXME, XXX) and returns findings with severity levels. Use this to audit code quality, identify incomplete work, or generate reports. Returns JSON with findings array and score count.'
• Document output schema in description or as a separate schema block: 'Returns {tool: string, findings: [{id: string, sev: string, where: string}], score: number}'
• Add parameter constraints: 'target must be a valid file system path (relative or absolute); max depth 10 levels; skips hidden dirs and common build artifacts (node_modules, .git, __pycache__)'
• Add error handling guidance: 'If path is invalid or inaccessible, returns error with available alternatives. If scan times out (>30s), returns partial results with timeout flag.'
• Clarify read-only nature: 'This tool only reads files; it does not modify the file system. Safe to call repeatedly.'