Single tool 'personagraph' has a reasonable description (67 chars, within 10-1024 range) but critical gaps in schema visibility and parameter documentation. The input schema shows two parameters (identifier, platforms) with basic type info, but lacks detailed descriptions for each parameter. No output schema is documented. The tool name lacks a clear action verb (should be 'resolve_identity' or 'search_identity'). Code inspection reveals the actual implementation is in personagraph/mcp_server.py using a wrapper (build_mcp_server), making the tool definition inferred rather than directly visible in source. The server appears to be a wrapper around an undocumented 'scan' function, creating ambiguity about what the tool actually does vs. what the description claims.

• Rename tool from 'personagraph' to 'resolve_identity' or 'search_identity' to follow verb_noun convention and clarify intent.
• Add detailed parameter descriptions: 'identifier' should specify accepted formats (email regex, phone pattern, username constraints); 'platforms' should list valid platform keys as an enum.
• Document the output schema explicitly. Specify all returned fields (e.g., 'matches', 'confidence', 'sources'), their types, and what they represent.
• Clarify the actual tool behavior. The description mentions identity resolution, but code samples show code scanning. Either update the description to match implementation or fix the implementation.
• Add error handling guidance. Specify what happens if identifier is invalid, if no matches are found, or if a platform is unavailable. Include recovery suggestions.