nucleo-mcp has 5 tools with clear naming (verb_noun pattern: nucleo_status, nucleo_search, nucleo_get, nucleo_list_sets, nucleo_save). Descriptions are present and contextual (avg ~150 chars), exceeding the 10-char minimum. All tools have input schemas with type definitions. However, parameter descriptions are sparse or missing in several tools (e.g., nucleo_status has empty properties; nucleo_list_sets has no params described). Output schemas are not documented. Error handling is minimal, no recovery guidance or actionable error messages visible in the code. The nucleo_save tool lacks explicit validation messaging for path traversal prevention, despite mentioning it in the description.

• Add explicit output schema documentation for each tool. Example for nucleo_search: 'Returns array of {id: number, name: string, style: string, size: number, pack: string, tags: string[]}'. This enables LLMs to chain calls and extract the right fields.
• Document error responses with recovery guidance. Example: 'If nucleo_search returns empty results, try nucleo_status to verify the library is loaded, then retry with a broader query.'
• For nucleo_save, add explicit validation error format: 'Invalid path: must be relative to project root and not contain .. or /. Example valid paths: icons/, icons/my-icon.svg'.
• Add parameter descriptions to nucleo_status and nucleo_list_sets input schemas (even if empty, add a note like 'No parameters required'). This clarifies intent.
• For nucleo_get and nucleo_search, document the disambiguation behavior: 'If multiple icons match the name, returns candidates array with {id, name, style, pack}. Retry with klass or set to narrow results.'