Skip to main content
Glama
carbase-mcp

carbase-mcp

by vollebergh

search

Find car versions in Carbase by brand, model, filters, and name keywords; retrieve list prices, fuel types, and version IDs for specification lookup or comparison.

Instructions

Search Carbase by brand, model and/or filters. Returns at most max_versions versions.

filters: filter key -> option value(s) or a range, keys and values from list_filters. e.g. {"fuel_type": ["elektrisch", "elektro-benzine"], "body": "suv", "price": {"max": 40000}, "year": {"min": 2022}} name_contains: keep only versions whose name contains all these words ("1.5 tsi"). sort: orders model generations (for "price": by their cheapest version) and, with "price", the versions inside each generation. It is not a global ranking of versions: for "the N cheapest", fetch more (e.g. max_versions=100) and compare the prices. cursor: next_cursor from a previous call with the same arguments, to continue.

Returns total_versions (Carbase's count, before name_contains), returned, next_cursor (null when there is nothing more) and model generations (model, body, years, price range), each with its versions (id, name, years, fuel, transmission, energy label, list price, bijtelling %). Prefer narrowing (filters, name_contains) over paging through hundreds of versions. Use a version id with get_specs or compare_versions.

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": "search"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNomake_model
brandNo
modelNoModel slug from list_models, e.g. 'golf'
cursorNo
filtersNo
descendingNo
max_versionsNo
name_containsNo

Output Schema

NameRequiredDescriptionDefault
hintYes
returnedYes
generationsYes
next_cursorYes
total_versionsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.2

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and delivers the non-obvious behaviors: total_versions counts before name_contains is applied, next_cursor is null at the end, cursor is only valid with identical arguments, and sort ordering semantics differ between generations and versions. It does not mention rate limits or error behavior, but for a read-only search these are minor.

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

Conciseness4/5

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

Front-loaded purpose sentence followed by per-parameter notes and a closing routing sentence — well organized and nearly all of it earns its place. The enumeration of returned version fields (id, name, fuel, bijtelling %, etc.) duplicates the output schema and could be trimmed.

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?

For an 8-parameter search tool with an output schema, the description covers the tricky parts: filter syntax, pagination, sort caveats, and the handoff to sibling tools. The only meaningful omission is the undocumented 'descending' flag, which is otherwise undocumented given low schema coverage.

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?

Schema description coverage is only 13%, so the description has to compensate; it does so for filters (with a concrete example and a pointer to list_filters), name_contains, sort, and cursor. The gap is 'descending', which appears in the schema but is never explained anywhere, and max_versions is only implied by the cap sentence.

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

Purpose5/5

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

States a specific verb and resource — searching Carbase car versions — plus the narrowing axes (brand, model, filters) and the cap (max_versions). It is distinguishable from list_brands/list_models/list_filters, which it explicitly defers slug and filter-key discovery to.

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

Usage Guidelines5/5

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

Gives explicit when-to guidance: prefer narrowing via filters/name_contains over paging hundreds of versions, and feed the returned version id into get_specs or compare_versions. It also warns that sort is not a global ranking and prescribes fetching more (e.g. max_versions=100) to find 'the N cheapest', which prevents a classic misuse.

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