Server provides 7 tools with complete input schemas and descriptions in Chinese. All tools follow verb_noun naming (get_*, create_*). Schemas are well-structured with type definitions and parameter descriptions. However, output schemas are not documented, LLMs cannot predict response structure for planning. Descriptions are adequate (100-200 chars) but lack actionable guidance on when to use each tool vs. alternatives. Error handling is minimal, no recovery guidance or categorization. No tool annotations (readOnlyHint/destructiveHint) despite clear risk levels. STDIO transport caps protocol readiness at 50.

• Document output schemas for all tools. Example: 'Returns {metadata: {scale: number, device: string}, pages: [{id: string, name: string, children: [...]}]}'. This enables LLMs to plan multi-step workflows.
• Add tool annotations via MCP protocol. Mark download_design_images with destructiveHint=true (writes to disk). Mark all get_* tools with readOnlyHint=true. This signals safety to LLM planners.
• Enhance error messages with recovery guidance. Example: 'Invalid URL format. Expected: https://app.mockplus.cn/app/{APP_ID}/develop/design/{PAGE_ID}. Call get_metadata first to discover valid page IDs.'
• Clarify tool relationships in descriptions. Add to get_design_data: 'Alias for get_design_context. Use get_design_context for new code.' Remove redundancy.
• Migrate from STDIO to HTTP+SSE or Streamable HTTP transport. This enables integration with hosted MCP clients and remote agent platforms. STDIO limits adoption to local CLI only.

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

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