Dutch vehicle report by licence plate: MOT, defects, odometer verdict and open recalls.
Scored across 1 tool
With only a single tool, there is no possibility of confusion or overlapping purposes. The tool's scope is clearly defined around retrieving verified vehicle context for a Dutch license plate.
The tool name 'get_verified_vehicle_context' follows a clear verb_noun pattern and is descriptive of its function. Despite being the only tool, it is internally consistent and unambiguous.
A single tool is on the borderline of being thin for a server with a specific purpose. However, the tool itself is comprehensive and may justify its lone existence, though typical expectation is 3-15 tools.
The tool covers all major aspects of Dutch vehicle context—identity, technical data, fuel, inspections, defects, odometer, recalls, status flags, value, signals, and provenance. It explicitly notes limitations (theft status not included) and provides guidance for edge cases like missing identity. For its stated purpose, it is effectively complete.
Geeft de geverifieerde context van een Nederlands voertuig op kenteken, uit het openbare kentekenregister en het terugroepregister. Gebruik dit bij elke vraag over een concrete Nederlandse auto, motor, bestelbus of aanhanger — bijvoorbeeld bij het beoordelen van een occasion, het controleren van de APK, of de vraag of er een terugroepactie openstaat.
Het antwoord heeft deze blokken: identity (merk, type, bouwjaar, leeftijd), technical, fuel (brandstof en emissieklasse), inspection (APK met historie), defects (afkeurpunten per keuring, mét terugkerende gebreken), odometer (oordeel over de kilometerstand), recalls (terugroepacties, open én afgehandeld, met defect, gevolg, gevaar en herstel), status_flags, value, signals en provenance.
signals zijn observaties, geen vastgestelde gebreken. Ze staan gesorteerd op ernst; begin daarmee. Let vooral op open_recall, odometer_illogical en recurring_defect — dat laatste betekent dat hetzelfde punt bij meerdere keuringen is afgekeurd.
BELANGRIJK, twee dingen. Ten eerste: als identity.found false is, bestaat het kenteken niet in het register en gaat de rest van het antwoord nergens over; meld dat dan in plaats van lege velden te presenteren. Ten tweede: of een voertuig als gestolen of vermist geregistreerd staat is NIET openbaar en staat hier dus niet in. Een rapport zonder diefstalmelding is geen bewijs dat een voertuig niet gestolen is — zeg dat er expliciet bij als iemand naar de betrouwbaarheid van een aankoop vraagt.
Dit is geen taxatie, geen technische keuring en geen aankoopadvies.
| Name | Required | Description | Default |
|---|---|---|---|
| depth | No | Hoeveel detail. 'compact' (standaard) geeft alleen de laatste keuring en kort de afgehandelde terugroepacties in; alle feiten en álle signalen blijven erin, en een openstaande terugroepactie blijft altijd volledig. Vraag 'full' voor de complete keuringshistorie en de bron-URL's. | |
| plate | Yes | Nederlands kenteken, met of zonder streepjes: '01-TH-FD', '01THFD' of '01 th fd' werken allemaal. Zes tekens. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It explains the output blocks, notes that 'signals' are observations not defects, and importantly warns about two critical behaviors: (1) if identity.found is false, the rest is meaningless, and (2) theft status is not public and not included, so absence of a theft report does not prove the vehicle is not stolen. It also states limitations (no valuation, etc.) without contradicting any annotations (none provided).
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?
The description is longer than a typical one-liner but well-structured: it starts with purpose, then lists output blocks, then explains signals, and ends with critical warnings. Each section carries essential information. While it could be trimmed (e.g., some repetition about signals), the organization and front-loading of usage make it efficient. It earns a 4 because it is appropriately sized for the complexity, but not perfectly minimal.
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?
Given the tool's complexity (multiple output blocks, special edge cases) and the absence of an output schema, the description does a good job explaining the response structure and critical warnings. It lists the block names and highlights crucial points like identity.found false and theft-status omission. However, it does not detail the exact fields within each block (e.g., 'value' or 'status_flags'), which might be necessary for agents to extract information correctly. It is complete enough for most use cases but not exhaustive.
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?
The schema description coverage is 100% for both parameters (plate and depth), so the baseline is 3. The description does not add significant meaning beyond the schema: it does not explain plate format (already in schema) or the depth behavior (also in schema). However, it does indirectly explain the output blocks which help interpret depth, but that's more about the response than the parameter itself. The description adds minimal parameter semantics beyond what the schema already provides.
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 clearly states the tool's function: 'Geeft de geverifieerde context van een Nederlands voertuig op kenteken' — gives verified context of a Dutch vehicle by license plate. It also provides concrete use cases (evaluating a used car, checking APK, open recalls) and distinguishes itself by being the go-to for any concrete vehicle question. Even without sibling tools, the purpose is unambiguous and specific.
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?
The description explicitly says to use this tool 'bij elke vraag over een concrete Nederlandse auto, motor, bestelbus of aanhanger' and gives examples. It also clearly states what it is NOT (not a valuation, not a technical inspection, not purchase advice), providing exclusions. This gives an agent clear guidance on when to invoke it and when not to rely on it for other purposes.
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.
get_verified_vehicle_contextRead-only Dutch vehicle knowledge, comparisons, terminology and cited sources for AI clients.
UK vehicle MOT status and full MOT history from official DVSA data, by registration.
Mechanic-grade used-car listing verdicts: risk score, failure points, repair costs, fair price.
US vehicle recalls, complaints, EPA figures, VIN decode and trouble codes, with sources.
Add one secure layer between your agents and this server.
