shojiku-mcp defines 5 tools with basic schemas and descriptions, but falls short of production quality. All tools have descriptions (10-80 chars, below the 194-char baseline), and input schemas are present but minimal. Parameters lack detailed constraints, format specifications, and dependency documentation. No output schemas are documented. Error handling is absent, tools return raw results with no recovery guidance. Tool names are reasonable (validate, render_preview, inspect_layout, capabilities, format_catalog) but descriptions are terse and lack WHEN/WHY context. No tool annotations (readOnlyHint, etc.). The server is read-only (low risk), but the definitions do not meet the bar for confident LLM tool selection.

• Expand tool descriptions to 100-200 chars. For validate: 'Validate Shojiku definitions, templates, and parameters against the schema. Returns validation errors with line numbers and remediation hints. Call this before render_preview to catch structural issues early.'
• Document output schemas for each tool. E.g., render_preview returns {success: bool, image_data: string (base64), error?: string}. This enables LLMs to chain tools and extract results.
• Add format constraints to string parameters. E.g., 'definitions (YAML string, max 100KB, must contain a root-level components or layouts key)' and 'params (JSON string, must be a valid JSON object)'.
• Add error handling with recovery guidance. E.g., if validate fails: 'Validation failed: [error details]. Review the YAML syntax and ensure all required fields are present. Call format_catalog to see available component types.'
• Add tool annotations to the schema. Mark all 5 tools with readOnlyHint: true since they do not modify state. This signals to LLMs that these tools are safe to call speculatively.