Skip to main content
Glama

Kalkulator B2B

Sprawdzenie firmy (GUS REGON i Biała lista)

company_check
Read-only

Sprawdza polską firmę po NIP w rejestrach publicznych: GUS REGON (nazwa, adres, rodzaj podmiotu, data zakończenia działalności), a z bankAccount — czy ten rachunek jest na Białej liście Ministerstwa Finansów dla tego NIP w dniu date, z identyfikatorem zapytania jako dowodem sprawdzenia (reguła przelewów powyżej 15 000 zł). Użyj przed przelewem do nowego kontrahenta albo przy fakturze od nieznanej firmy. Nie podaje statusu VAT ani listy rachunków firmy. Rejestry mają dzienne limity — nie sprawdzaj tej samej firmy dwa razy.

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": {
      "nip": "<nip>"
    },
    "name": "company_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
nipYesNIP firmy — 10 cyfr, np. 5261040828, 526-104-08-28 albo PL5261040828
dateNoDzień, na który czytać Białą listę (RRRR-MM-DD), np. dzień zlecenia przelewu; domyślnie dziś (czas polski). Nie z przyszłości
bankAccountNoNumer rachunku z faktury albo do przelewu (26 cyfr, z „PL” albo bez, spacje dowolne) — sprawdzę, czy jest na Białej liście tej firmy w dniu date. Bez niego rachunek nie jest sprawdzany

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare a safe, read-only, open-world call, and the description goes well beyond them: it discloses the return payload, that a query identifier is produced as proof of the check for the >15 000 zł transfer rule, that the whitelist is evaluated as of a specific date, and that registries impose daily limits. It also declares what is NOT returned, which prevents wasted calls.

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?

Every sentence carries information - capability, trigger, exclusions, limits - with no filler. The opening sentence is long and multi-clause, packing the account branch into the same breath as the registry lookup, so it is dense rather than perfectly front-loaded.

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

Completeness5/5

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

There is no output schema, and the description compensates fully by enumerating what comes back and what does not. For a three-parameter read tool with a conditional account check, the agent has everything needed to call it correctly and interpret the result.

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 100%, so the baseline is 3. The description still adds cross-parameter meaning the schema does not: bankAccount only triggers the whitelist lookup and the lookup is anchored to the date parameter. Minor gain only, since the date default and format are already documented in the schema.

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?

Names the concrete verb (sprawdza), the resource (polską firmę po NIP) and the exact registries queried (GUS REGON, Biała lista MF), plus the fields returned (nazwa, adres, rodzaj podmiotu, data zakończenia działalności). It also states the conditional branch: with bankAccount it verifies the account against the whitelist for that NIP. That is enough to separate it from any sibling without opening the 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?

Explicit trigger conditions are given: before a transfer to a new counterparty, or when handling an invoice from an unknown company. Exclusions are stated just as clearly ('Nie podaje statusu VAT ani listy rachunków firmy') along with an operational caution about daily registry limits and not re-checking the same company.

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