Decode a 17-character VIN to make, model and year, with a link to the full vehicle history report.
Scored across 1 tool
There is only one tool, so there is nothing to confuse it with. Its purpose (decode a 17-character VIN and return a report link) is unambiguous and clearly scoped to a single action.
The single tool follows a clean verb_noun snake_case pattern (check_vin) that reads predictably. With only one name there are no convention clashes to introduce inconsistency.
One tool is defensible for a narrow VIN-lookup service, but the surface feels thin — no batch check, no separate report-fetch or VIN-validation operation. It sits at the borderline of 'under-scoped' rather than clearly well-scoped.
For its stated purpose the tool is essentially complete: it decodes make/model/year and hands off to the full history report, which covers the downstream needs (mileage, damage, stolen check, recalls, valuation). Minor gaps only, such as batch lookups or structured retrieval of report data for multiple vehicles.
Check a used car by its 17-character VIN (vehicle identification number). Returns the car's make, model and model year as decoded by Carlytics, plus a link to the free result page where the buyer can unlock the full vehicle history report (mileage records, inspection history, damage records where available, stolen-vehicle check, recalls, valuation). Use it whenever the user shares a VIN or asks whether a specific used car is OK to buy. Always show the user the report link.
| Name | Required | Description | Default |
|---|---|---|---|
| vin | Yes | The 17-character VIN, as the user wrote it. Spaces and lowercase are fine. | |
| language | No | The user's language or market code for the result page, e.g. 'de' for German, 'pl' for Polish, 'us' for the United States. Omit if unsure. |
| Name | Required | Description |
|---|---|---|
| vin | Yes | |
| make | Yes | |
| year | Yes | |
| model | Yes | |
| reportUrl | Yes |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. Beyond that, the description explains the two-tier behavior — a free decoded summary plus a paid/unlockable history page — and mandates surfacing the link, which is real behavioral context the annotations cannot convey.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with what it does, then what it returns, then when to use it. The middle sentence is long due to the enumeration of report contents, but each item is informative rather than filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
An output schema exists, so return values needn't be explained field by field, and the description still adds the business behavior (link to unlock the full report) and the display obligation. For a two-parameter read tool with full schema coverage and rich annotations, nothing an agent needs is missing.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, with the vin parameter documented (spaces/lowercase tolerated) and the language enum fully described, so the schema carries the parameter burden. The description reinforces the 17-character rule but adds nothing about the language/market parameter, which is appropriate for the baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific verb (check/decode) and resource (used car by 17-character VIN) and states exactly what comes back: make, model, model year, plus a report link. There are no siblings to disambiguate against, and an agent can tell from the first sentence what the tool does.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It gives an explicit trigger — 'whenever the user shares a VIN or asks whether a specific used car is OK to buy' — plus an operational instruction to always show the report link. It stops short of stating when not to use it (for example, an incomplete or non-VIN identifier), but the 17-character constraint earlier partially covers that.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
check_vinDecode any VIN and check open NHTSA safety recalls. Free official US government data, no auth.
Decode VINs, search recalls, complaints, crash ratings, and investigations.
Check a US car: decode a VIN, see recalls, crash ratings, owner complaints and fuel economy.
Decodes US VINs and looks up open NHTSA safety recall campaigns for a vehicle.
Add one secure layer between your agents and this server.
