Skip to main content
Glama

Check VAT ID

check_vat_id
Read-onlyIdempotent

Checks one EU VAT ID (27 member states plus XI) or one Swiss UID live in the official register (VIES or the Swiss UID register). Returns valid / invalid / unavailable / format_error, the registered name and address where published, the source with the time of the check (UTC) and a ready-to-file record. Accepts any common spelling (spaces, dots, dashes, lower case, 'MWST'). Use before reverse-charge invoices or to verify a business partner.

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": {
      "vat_id": "<vat_id>"
    },
    "name": "check_vat_id"
  }
}

Input Schema

NameRequiredDescriptionDefault
vat_idYesThe VAT ID or Swiss UID, with country prefix, e.g. DE123456788, ATU12345675 or CHE-123.456.788 MWST.
with_receiptNoOptional, default false. Set true only when the user asks for a signed receipt of this check for their files.
expected_cityNoOptional: expected city, compared by VIES.
expected_nameNoOptional: the company name you expect. VIES compares it with the register where the country supports this (e.g. Spain).
expected_streetNoOptional: expected street, compared by VIES.
requester_vat_idNoOptional: the user's OWN EU VAT ID. If given, VIES returns a consultation number as official proof of the check. Only pass it when the user provided their own VAT ID for this purpose.
expected_postal_codeNoOptional: expected postal code, compared by VIES.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedInput schema / additionalProperties
      Added value: +false
    • changedInput schema / properties / vat_id / description
      Previous value: -"The VAT ID or Swiss UID, with country prefix, e.g. DE123456789, ATU12345678 or CHE-123.456.789 MWST."New value: +"The VAT ID or Swiss UID, with country prefix, e.g. DE123456788, ATU12345675 or CHE-123.456.788 MWST."
    • addedInput schema / properties / with_receipt
      Added value: +{
      +  "description": "Optional, default false. Set true only when the user asks for a signed receipt of this check for their files.",
      +  "type": "boolean"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare readOnly/openWorld/idempotent/non-destructive, and the description goes well beyond them: it discloses the four possible outcomes (valid, invalid, unavailable, format_error), what data comes back (registered name and address 'where published'), provenance (source plus UTC time of check), and that a ready-to-file record is produced. It also flags input tolerance for arbitrary spellings, which tells the agent it need not pre-normalize.

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?

The core capability and its scope lead the first sentence, supported-source and normalization details follow, and the use cases close. With no output schema, the enumeration of return states earns its space; no sentence is redundant or restates the title.

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 seven-parameter, annotation-covered, output-schema-less tool this is close to complete: inputs, outcomes, provenance and use case are all covered. It stops short of explaining what 'unavailable' means operationally (retry vs. give up) or any rate limits on live register calls, which an agent would benefit from knowing.

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 and the schema already explains all seven parameters. The description adds real meaning on top by clarifying that vat_id accepts spaces, dots, dashes, lower case and 'MWST', which is not spelled out in the schema's example-only format guidance, and by scoping the tool to exactly one identifier.

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 (checks), a precisely bounded resource (one EU VAT ID across 27 member states plus XI, or one Swiss UID), and the authoritative source (VIES or the Swiss UID register). The word 'one' plus 'live in the official register' separates it from the plural sibling check_vat_ids and from format-only validators such as validate_vat_format.

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

Usage Guidelines4/5

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

Gives concrete when-to-use triggers: 'before reverse-charge invoices' and 'to verify a business partner'. It implies the live-register check is the right call versus a pure format check, but it never names an alternative tool or states a when-not condition (e.g. bulk checks belong to check_vat_ids).

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