MCP server for verifying replacement part fitment against vehicle specifications using OEM numbers, vehicle K-types, and VINs
Single tool 'execute_skill_action' has a reasonable name starting with verb, but critical gaps undermine quality. Description is 87 chars (below 10-char minimum for actionable guidance). Input schema visible with 3 parameters, all typed as strings with descriptions, but lacks enums, ranges, or validation constraints. No output schema documented anywhere, LLM cannot predict return structure. No error handling guidance. Tool appears functional but severely under-specified for production use.
Execute the universal replacement part fitment verification skill
No output schema documented. LLM cannot predict return structure (fields, types, pagination). Forces guessing and downstream failures.
Tool description is 87 characters, too terse. Does not explain WHEN to use it, WHAT it returns, or prerequisites. Baseline for A+ tools is 194 chars (p10=34, p90=392).
Input parameters lack constraints. 'part_oem_number', 'target_vehicle_ktype', 'vin' are free-form strings with no enums, patterns, length limits, or format specs. LLM will hallucinate invalid values.
No error handling guidance. Tool does not document what errors are possible, whether they are retryable, or what the LLM should do next (e.g., 'Part not found. Try a different OEM number.').
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 42 | 2026-07-28+ | v2 |
Tool implementation in mcp_server.py is a stub, prints JSON header but does not actually handle tool calls or invoke the client logic. No request/response loop visible.