Single tool 'create-mermaid-diagram' has a well-structured schema with 10 parameters, all typed and described. Naming follows verb_noun pattern (create_*). Description is 108 chars, within the 10-1024 baseline. However, the description lacks critical context: it does not explain WHEN to use this tool vs alternatives, what prerequisites exist, or what the output structure contains. Parameter descriptions are present but terse (avg ~30 chars vs 72 baseline). No output schema documented, LLMs cannot predict response structure. Error handling is generic (McpError wrapper) with no recovery guidance. The tool accepts file write operations (save_file action) but lacks security warnings about path traversal or permission checks.

• Document the output schema for both actions: 'get_url' returns {edit_url, view_url, download_url}; 'save_file' returns {file_path, format, size_bytes}. Include example responses.
• Expand tool description to 150-200 chars: explain that this tool converts Mermaid diagram syntax into viewable/editable URLs or downloadable files; mention it requires valid Mermaid syntax (flowchart, sequence, state, etc.).
• Add security note to 'outputPath' parameter: 'Must be a relative path within the working directory. Absolute paths and '..' traversal are rejected.'
• Enhance parameter descriptions: 'diagram' → 'Valid Mermaid diagram syntax (flowchart, sequence, state, class, etc.). Max 50KB. See https://mermaid.js.org for syntax reference.'
• Implement structured error responses: 'Invalid Mermaid syntax: line 5, unexpected token. Valid diagram types: flowchart, sequence, state, class, er, gantt, pie, git.' Include retry guidance.