Five tools with basic verb-noun naming and present descriptions, but significant gaps in parameter documentation and output schema clarity. All tools have input schemas with types, but parameter descriptions are minimal (averaging 20-30 chars, well below the 72-char baseline). No output schemas documented. Error handling is absent, no recovery guidance, no categorization of error types. Tool descriptions are adequate (40-60 chars) but lack context on when to use each tool vs. alternatives. No parameter constraints (enums, ranges, patterns) despite format/scale parameters accepting arbitrary values. Validation occurs server-side but errors are not documented in tool descriptions.

• Document output schemas for all tools. Example: get_figma_file returns {file_id: string, name: string, pages: array, components: array}. This enables LLMs to chain calls and extract required fields.
• Expand parameter descriptions to 50-100 chars with format/constraint details. E.g., 'file_key: Alphanumeric Figma file identifier (2-50 chars, found in file URL after /file/)' instead of 'The Figma file key'.
• Add enum constraint to export_assets 'format' parameter: {type: 'string', enum: ['png', 'jpg', 'svg', 'pdf']}. Add min/max to 'scale': {type: 'number', minimum: 0.5, maximum: 4}.
• Add error handling guidance to tool descriptions. E.g., 'Returns error if file_key is invalid (must be alphanumeric). Try searching for the file name in Figma UI to find the correct key.'
• Add pagination to list_components and list_styles: accept 'limit' (default 20, max 100) and 'offset' parameters. Return {items: [...], total: N, has_more: boolean} to enable iteration over large result sets.

Inferred effective spec: <=2025-11-25.

• Relies on Logging (deprecated) - log to stderr or use OpenTelemetry