Vedit MCP has 7 tools with Italian descriptions and basic schemas. All tools have input schemas with type definitions and parameter descriptions, which is positive. However, descriptions are extremely brief (10-30 chars), falling well below the 50-200 char LLM-optimized baseline. Parameter descriptions are minimal and lack actionable context. No output schemas are documented. Error handling is absent, tools provide no recovery guidance. Tool naming uses verb_noun pattern (project_create, project_open) which is good, but descriptions don't explain WHEN to use each tool or what distinguishes them. The server is STDIO-only, which is a hard transport limitation.

• Expand all tool descriptions to 80-150 chars in English. Example: 'project_create' → 'Create a new video project with specified resolution, frame rate, and preset. Sets it as the current project. Use this to initialize a new editing session before adding clips.'
• Document output schemas for all tools. Specify what fields each tool returns (e.g., project_info returns {timeline: [...], duration: number, tracks: [...]}) so LLMs can chain calls.
• Add error recovery guidance to descriptions. E.g., 'project_open: Opens an existing project file. If file not found, call project_info to list available projects or project_create to start a new one.'
• Declare enums for constrained parameters. Convert 'preset' description to an enum: ['1080p', '1080p60', '4k', '720p', 'vertical', 'vertical60', 'square']. Add min/max to width, height, fps, sample_rate.
• Translate all descriptions to English and add parameter-level descriptions explaining the purpose of optional fields like 'detail' in project_info (normal vs full verbosity).