Critical gaps across all dimensions. Tool descriptions are present but minimal (10-50 chars, well below 194-char baseline). Input schemas lack proper type definitions and parameter descriptions, most parameters have no description field at all. No output schemas documented. Error handling absent. Security concerns: quit tool is destructive with no confirmation pattern. Tools appear inferred from HTTP handlers rather than explicitly registered with full MCP schemas. No pagination, no idempotency markers, no recovery guidance.

• Expand all tool descriptions to 100-200 characters. Include WHAT the tool does, WHEN to use it (vs similar tools), and what it returns. Example: 'Retrieve the current diagram content and version. Use this to read the editor state before making updates. Returns {content: string, version: number}.'
• Add explicit input schemas with type and description for every parameter. For set_preferences, document the expected JSON structure (e.g., 'JSON object with keys like vimMode (boolean), theme (string: dark|light|auto)').
• Document output schemas for all tools. Specify field names, types, and whether fields are always present or conditional. Example for get_diagram: '{content: string, version: number, lastModified: ISO8601-string}'.
• Add a confirmation step for destructive operations. Implement a 'quit_confirm' tool that returns {action: 'quit', requiresConfirmation: true} and requires explicit user approval before calling quit.
• Add error handling guidance. For set_diagram, document what happens if content is invalid Mermaid syntax. Return structured errors like {error: 'invalid_syntax', line: 5, message: 'Unexpected token'}.