Skip to main content
Glama

Estimate a used-car price

estimate_price
Read-onlyIdempotent

Rule-based price range (low/mid/high) for a used car from its VIN or Dutch plate (or make/model/year), mileage and condition (since 5.11.2026 the website itself shows the official Spanish Hacienda value instead; this tool keeps the rule-based estimate). Price when new, in this order: newPrice, the RDW list price of a Dutch plate, the typical new price of the make + model + year from RDW open data (about 500 listed models; vehicle.make and vehicle.model are matched by name), else a car class (small, compact, family, suv, premium). Not a valuation; it explains every step and the typical dealer gap. In EUR; with country PL the result is in PLN (EUR sources converted at the ECB reference rate, class bands in PLN). Nothing is stored.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "estimate_price"
  }
}

Input Schema

NameRequiredDescriptionDefault
kmNo
vinNo
langNoLanguage of the explanation
plateNoDutch plate (RDW)
countryNoOptional market; PL gives the result in PLN
vehicleNoInstead of VIN/plate or as overrides: make, model, year, firstRegistration (YYYY-MM-DD), listPrice
carClassNoOptional car class when the model is not listed and the price when new is unknown: small, compact, family, suv or premium
newPriceNoApproximate price when new in EUR (needed when the decoder has no list price, unless carClass is given)
conditionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / properties / carClass
      Added value: +{
      +  "description": "Optional car class when the model is not listed and the price when new is unknown: small, compact, family, suv or premium",
      +  "enum": [
      +    "small",
      +    "compact",
      +    "family",
      +    "suv",
      +    "premium"
      +  ],
      +  "type": "string"
      +}
    • addedInput schema / properties / country
      Added value: +{
      +  "description": "Optional market; PL gives the result in PLN",
      +  "enum": [
      +    "DE",
      +    "FR",
      +    "ES",
      +    "IT",
      +    "PL",
      +    "NL"
      +  ],
      +  "type": "string"
      +}
    • changedInput schema / properties / newPrice / description
      Previous value: -"Approximate price when new in EUR (needed when the decoder has no list price)"New value: +"Approximate price when new in EUR (needed when the decoder has no list price, unless carClass is given)"
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already cover read-only, idempotent, non-destructive, so the description rightly spends its space elsewhere: 'Nothing is stored', the ECB reference rate conversion for PL with class bands in PLN, and the fact that the result explains every step plus the typical dealer gap. The 5.11.2026 Hacienda note adds genuine provenance context, though it is worded ambiguously enough to slow the reader down.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The output-critical scope statement is front-loaded, but the body is one long comma-spliced run with nested parentheticals, including the date-stamped Hacienda aside that interrupts the price-derivation explanation. Every piece of information is relevant, yet the structure makes it harder to parse than it needs to be.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

There is no output schema, so the description carries the return-value burden and does so: a low/mid/high range in EUR or PLN plus a step-by-step explanation and dealer-gap note. Combined with the currency and fallback rules, an agent has enough to call it correctly and interpret the result; only the vehicle sub-object and condition/km effects are left implicit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 67% schema coverage the description compensates well: it defines the precedence chain for price when new (newPrice, then RDW list price for a Dutch plate, then RDW open-data typical new price matched by make/model name, else carClass), and clarifies that vehicle fields act as overrides alongside VIN/plate. It still leaves km, condition, and firstRegistration/listPrice semantics to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first clause gives a specific verb and resource: a rule-based low/mid/high price range for a used car, with the accepted inputs (VIN, Dutch plate, or make/model/year plus mileage and condition). It is clear what the tool produces and what it consumes, though it never names sibling tools such as decode_vehicle to sharpen the boundary.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage context is implied rather than stated: the fallback ordering for price-when-new tells the agent what inputs are needed, and 'Not a valuation' sets an expectation about the output. There is no explicit when-to-use/when-not statement and no routing advice against decode_vehicle or the listing tools, so the agent must infer the alternative.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources