Skip to main content
Glama

VeriActa: activity and product classifications

classification_lookup
Read-onlyIdempotent

A country's official activity or product classification: the details of a code (what it includes and excludes, its counterparts in other versions), the codes closest to a description, or the classification's rules. Use it to choose a code for a business activity or for a product or service, or to check what a code covers. Candidates are the closest matches even when none fits, and a high score does not confirm a classification: read what each includes and excludes. For a tax rule that depends on the code, call law_lookup next.

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": {
      "jurisdiction": "<jurisdiction>",
      "system": "<system>",
      "query": "<query>"
    },
    "name": "classification_lookup"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNoauto (default): codes in the query give their details, anything else is a search. search: candidates for a description. rules: the classification's rules.
limitNoCandidates a search returns (1 to 10, default 5).
queryYesCodes of the system, a concrete description of the activity, product or service to classify (what exactly, for whom), or a question about the classification's rules.
systemYesThe classification: PKD (Polish business activities) or PKWiU (Polish goods and services). `jurisdictions` lists each country's systems.
versionNoThe version of the codes in the query, when you know it (PKD: 2025 or 2007; PKWiU: 2015 or 2025).
jurisdictionYesThe country whose law or register is asked about, by its ISO code (EU: the law of the European Union itself). Live: PL, ES, EU, DE, DK.

Output Schema

NameRequiredDescriptionDefault
modeNoWhat was asked: a code, a description to classify, or the classification's rules.
codesNoThe codes asked for: name, what each includes and excludes, and its counterparts in the other version.
rulesNoClassification rules that apply.
sourceNoThe regulations and the official files the classification comes from.
appliesNoWhich version of the classification applies to what and until when.
warningsNoNotes to read before answering: what was not found, not confirmed or may be out of date.
candidatesNoThe codes closest to the description; a high score does not confirm the classification.
candidates_noteNoWhat candidates are and are not.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / jurisdiction / description
      Previous value: -"The country whose law or register is asked about, by its ISO code (EU: the law of the European Union itself). Live: PL, ES, EU, DE."New value: +"The country whose law or register is asked about, by its ISO code (EU: the law of the European Union itself). Live: PL, ES, EU, DE, DK."
    • changedInput schema / properties / jurisdiction / enum
      Previous value: -[
      -  "PL",
      -  "ES",
      -  "EU",
      -  "DE"
      -]New value: +[
      +  "PL",
      +  "ES",
      +  "EU",
      +  "DE",
      +  "DK"
      +]
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered without the description. The description still adds high-value behavioral context that no annotation covers: candidates are the closest matches even when none fits, and a high score does not confirm a classification, so includes/excludes must be read. It omits any note on latency, but for a lookup tool that is 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?

The definition is front-loaded with the resource, then usage, then a warning, then a sibling handoff, and each sentence carries information. The long first sentence with nested parentheticals is dense but not padded; it could be split without adding content.

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 a six-parameter tool with three required inputs, an output schema and full annotation coverage, the description covers purpose, usage and result-reliability caveats. Return-shape details are unnecessary because an output schema exists, and the remaining gaps are minor phrasing rather than missing decision-relevant information.

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

Parameters3/5

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

With 100% schema description coverage, the schema already explains mode, limit, query, system, version and jurisdiction. The description only loosely echoes them ('details of a code', codes closest to a description, the classification's rules) and adds no syntax or formatting detail beyond the schema. Baseline 3 applies.

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?

The description states a specific resource (statistical classification: PKD/PKWiU) and names the three things it returns: details of a code, closest codes to a description, and the classification's rules. It also distinguishes the tool from its sibling by saying that a tax rule needs law_lookup instead, so an agent can tell them apart without opening either schema.

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?

It gives explicit when-to-use guidance ('to choose a code for a business activity or for a product or service, or to check what a code covers') and an explicit when-to-use-another rule ('For a tax rule that depends on the code, call law_lookup next'). The handoff condition is concrete rather than implied.

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.