Five tools with complete input schemas and clear descriptions. All tools follow verb_noun naming (get_*, list_). Descriptions are well-written (100-200 chars, within baseline 194 avg). Parameters have types and descriptions. However, output schemas are NOT documented, LLMs cannot predict response structure. Error handling is minimal (only 'connection_required' shown). No tool annotations (readOnlyHint, etc.). Parameter descriptions lack format constraints (e.g., 'file_key' should specify format). No pagination support documented for list_comments despite potentially large result sets.

• Document output schemas for all tools. Example: get_me returns {id: string, email: string, handle: string, img_url: string}. Include field types and descriptions so LLMs can plan downstream calls.
• Add tool annotations to input schemas. Mark all five tools with readOnlyHint: true to signal they are safe to call without confirmation.
• Enhance parameter descriptions with format constraints. E.g., file_key: 'The Figma file key (alphanumeric, 20-30 chars, extracted from URL after /file/ or /design/).'
• Add pagination to list_comments: accept limit (1-100, default 20) and cursor parameters; return total_count and next_cursor in response.
• Improve error responses with actionable guidance. E.g., 'Invalid file_key: not found. Verify the key is correct and you have access to the file.' instead of raw HTTP status.