SEO Researcher has 6 tools with basic naming and descriptions, but significant gaps in schema completeness and parameter documentation. All tools follow verb_noun naming (seo_research_*), which is good. Descriptions are present but brief (10-50 chars), below the 50-200 char baseline for LLM-optimized docs. Critical issue: input schemas lack type information for most parameters. The 'research_type' parameter in seo_research_start has no enum constraint despite accepting only 'standard' or 'deep'. Parameter descriptions are minimal or absent. No output schemas documented. Error handling and recovery guidance are not visible in the provided code. Tools are read-only except seo_research_start, which is appropriate for risk classification.

• Expand tool descriptions to 50-200 characters. Include WHAT the tool does, WHEN to use it, and any prerequisites. E.g., 'Check current research usage and remaining units. Call this before seo_research_start to verify you have units available.'
• Add enum constraint to seo_research_start 'research_type' parameter: {"enum": ["standard", "deep"], "description": "Type of research: standard (1 unit) or deep (2 units)"}
• Document output schemas for all tools. Specify which fields are returned (e.g., job_id, status, results, error_message) and their types. This enables LLMs to chain calls and extract required data.
• Add min/max bounds to seo_research_list 'limit' parameter: {"type": "number", "minimum": 1, "maximum": 100, "description": "Maximum number of jobs to return (1-100, default 20)"}
• Add error handling guidance to tool descriptions. E.g., 'If job_id is invalid, returns 404 with message. Try seo_research_list to find valid job IDs.' This guides LLM recovery.

Inferred effective spec: 2025-06-18+.

• Relies on Stateful initialize / Mcp-Session-Id (removed; protocol is stateless) - make each request self-contained