Loading ToolBench
Decode VINs, search recalls, complaints, crash ratings, and investigations via MCP. STDIO or Streamable HTTP.
Strong foundational quality with well-structured tool definitions, comprehensive parameter schemas, and clear descriptions. All 5 tools have properly typed input schemas with descriptions. Tool names follow verb_noun convention (nhtsa_decode_vin, nhtsa_get_safety_ratings, etc.). Descriptions are action-oriented and contextual (50-250 chars, well within the 10-1024 baseline). Parameter descriptions are present and explain constraints (e.g., 'up to 50 VINs for batch decode', 'Partial VINs accepted, use * for unknown positions'). All tools are READ_ONLY, reducing risk. However, output schemas are not explicitly documented in the visible source, the code references them but does not show return type declarations. Parameter enums are used effectively (nhtsa_lookup_vehicles operation enum). Error handling guidance is absent from descriptions, no recovery hints like 'If VIN decode fails, try nhtsa_lookup_vehicles()' or explanation of what happens when a rating is unavailable. Batch capability in nhtsa_decode_vin is well-designed but other tools lack batch variants despite being good candidates (e.g., search_complaints, get_safety_ratings for multiple vehicles). Pagination is implemented but not consistently explained in descriptions.
Decode a Vehicle Identification Number to extract make, model, year, body type, engine, safety equipment, and manufacturing details. Pass a single 17-character VIN string, or an array of up to 50 VINs for batch decode. Partial VINs accepted — use * for unknown positions.
Get NCAP crash test ratings and ADAS feature availability for a vehicle. Use when the user specifically wants crash test stars, rollover risk, or wants to compare safety features across vehicles. NCAP data available from 1990+, best coverage for 2011+.
Composite vehicle safety profile tool — combines recalls, complaints, and crash test ratings into a single response.
Look up valid makes, models, and vehicle types in NHTSA's database. Use to resolve ambiguous vehicle names, find correct make/model spelling, or discover what models a manufacturer produces.
Search consumer safety complaints filed with NHTSA for a specific vehicle. Returns a component breakdown over all matching complaints plus a paginated slice of the most recent complaints. Use for common problems, failure patterns, or owner-reported issues.
Output schemas are not explicitly documented in descriptions or visible schema definitions. While parameters are well-typed, the return structures are inferred from tool names and descriptions rather than formally declared. Tools returning componentBreakdown, pagination metadata, and crash test results lack return-type guidance.
Error handling and recovery guidance is absent from all tool descriptions. When a VIN is invalid, NCAP data is unavailable, or no complaints exist, descriptions do not explain what to do next or which tool to call for fallback.
Parameter naming inconsistency: nhtsa_get_safety_ratings uses vehicleId (camelCase) while other parameters follow snake_case (make, model, modelYear). This breaks the naming convention expected by agents.
Inferred effective spec: 2026-07-28+.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | C | 67 | 2026-07-28+ | v2 |
No batch variants offered for tools that agents might call in loops. nhtsa_search_complaints, nhtsa_get_safety_ratings, and nhtsa_get_vehicle_safety accept single vehicles only. Agents querying multiple vehicles must call these tools N times instead of once with arrays.
Discovery guidance missing from nhtsa_lookup_vehicles description. No hint that this tool should be called when vehicle names are ambiguous or spelling is uncertain, agents may skip it and pass malformed make/model strings to other tools.