Skip to main content
Glama
carbase-mcp

carbase-mcp

by vollebergh

compare_versions

Compare 2–5 vehicle versions by section and field in version ID order, and optionally show only differing values to identify specification changes.

Instructions

Compare 2-5 versions: per section and field, the values in version_ids order.

only_differences drops fields that are equal for all versions.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "version_ids": "<version_ids>"
    },
    "name": "compare_versions"
  }
}

Input Schema

NameRequiredDescriptionDefault
sectionsNoSection names to keep, e.g. ['PRESTATIES']
version_idsYes
only_differencesNo

Output Schema

NameRequiredDescriptionDefault
versionsYes
comparisonYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.2

TDQS

A3.7/5.0
Behavior3/5

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

No annotations exist, so the description carries the full burden. It does disclose genuinely useful behavior: results are grouped per section and field, column order follows version_ids, and only_differences (default true) drops fields equal across all versions. It says nothing about how missing/invalid version IDs, permission requirements, or empty diff results are handled.

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

Conciseness5/5

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

Two short sentences, front-loaded with what the tool produces, then the one flag that changes output. Nothing is wasted and nothing needs re-reading.

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?

With an output schema present, the description correctly does not restate return values, and for a three-parameter tool it covers the key call-shaping facts. The remaining gap is discovery-level detail — valid section names and error behavior for out-of-range or unknown version IDs.

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 coverage is only 33% — just `sections` is documented — and the description compensates for both remaining parameters: it explains the 2-5 bound on version_ids, that output columns follow version_ids order, and the exact semantic of only_differences ('drops fields that are equal for all versions'). Only `sections` filtering semantics (what happens with an unknown or absent section) is left thin.

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?

States a specific verb and resource ("Compare ... versions") plus the scope (2-5 versions) and the shape of the result (per section and field, ordered by version_ids). No sibling is named as an alternative, and none of the listed siblings (get_fields, get_specs, list_*, search) is an obvious substitute for a version diff, so the lack of differentiation costs little.

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 is implied by the name and by the 2-5 constraint, but the description never says when to prefer this over fetching individual versions (e.g. get_specs) or what to do when more than five versions are needed. No exclusions or prerequisites are given.

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