Skip to main content
Glama

Factur-X: Generate & Validate E-Invoices

Check one invoice party

check_party
Read-onlyIdempotent

Check exactly one seller or buyer's registry identifiers and readiness through EU Verify.

Use to correct one party's identifiers; use check_invoice_parties to check seller and buyer together,
or validate_invoice for document rules.
Supply siren, siret or vat; siret wins over siren. A SIREN/SIRET, country_code=FR or FR VAT triggers
French checks requiring a SIREN/SIRET. Omitted vat can be derived from a successful French lookup;
foreign parties normally need explicit VAT. Send address fields with a coherent country_code;
requester_vat cannot substitute for the checked party's vat.

Sends supplied fields to EU Verify and applicable registers. A Pro/Scale key enables checks;
other plans return plan_excluded. No Factur-X document quota is consumed.
Returns status, reasons with field pointers and available evidence: invoice_ready is positive,
not_ready needs correction, upstream_unavailable is inconclusive and retryable, invalid_input
indicates rejected input. Register results and evidence ids may change between calls.
No invoice is created or stored.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
vatNoParty's EU VAT number, for example FR40732829320.
cityNoCity, checked with the address.
eoriNoEORI. Checked only when you send it.
ibanNoParty IBAN. Checked only when you send it.
roleNoParty role recorded in the evidence; defaults to buyer.buyer
sirenNo9-digit French SIREN, including leading zeros.
siretNo14-digit French SIRET, including leading zeros.
addressNoStreet line; any address, postal_code or city activates address checking.
postal_codeNoPostal code, checked with the address.
country_codeNoISO 3166-1 alpha-2 country code, for example FR or DE.
requester_vatNoYour VAT number, so the evidence pack can include a VIES request identifier.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / country_code / description
      Previous value: -"ISO 3166-1 alpha-2. FR, a SIREN, or a VAT starting with FR makes the party French."New value: +"ISO 3166-1 alpha-2 country code, for example FR or DE."
    • changedInput schema / properties / siren / description
      Previous value: -"9-digit French SIREN. Give siren, siret, or vat."New value: +"9-digit French SIREN, including leading zeros."
    • changedInput schema / properties / siret / description
      Previous value: -"14-digit SIRET. French parties need a SIREN or SIRET."New value: +"14-digit French SIRET, including leading zeros."
    • changedInput schema / properties / vat / description
      Previous value: -"EU VAT number, for example FR40732829320. Checked, or derived from the SIREN."New value: +"Party's EU VAT number, for example FR40732829320."
  2. Changed3 schema fields changed
    • changedInput schema / properties / address / description
      Previous value: -"Street line. Checked only when you send an address."New value: +"Street line; any address, postal_code or city activates address checking."
    • changedInput schema / properties / iban / description
      Previous value: -"Seller IBAN. Checked only when you send it."New value: +"Party IBAN. Checked only when you send it."
    • changedInput schema / properties / role / description
      Previous value: -"seller or buyer. Required."New value: +"Party role recorded in the evidence; defaults to buyer."
  3. Added

TDQS

A4.8/5.0
Behavior5/5

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

With annotations only covering read-only/open-world/idempotent, the description adds substantial context they don't: fields are sent to EU Verify and applicable registers, a Pro/Scale key is required (other plans return plan_excluded), no Factur-X quota is consumed, no invoice is stored, and results may drift across calls. It even decodes the status vocabulary (invoice_ready, not_ready, upstream_unavailable, invalid_input).

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 with purpose then alternatives, then rules, then behavior. The dependency/precedence block is dense, but every sentence carries information an agent needs; only minor tightening is possible.

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?

For an 11-param external-check tool with an output schema, the description covers plan gating, quota, side-effect absence, status semantics, and identifier resolution rules. Nothing required to call it correctly is missing.

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 baseline is 3, but the description adds real precedence/derivation semantics not in the schema: siret wins over siren, omitted vat can be derived from a successful French lookup, foreign parties need explicit VAT, country_code=FR triggers French checks, and requester_vat cannot substitute for the checked party's vat.

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 (check) and resource (exactly one seller or buyer's registry identifiers) plus the backing service (EU Verify). It explicitly contrasts with check_invoice_parties, so the agent can distinguish the two single-vs-batch tools without opening a 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?

Names the exact alternatives and the condition selecting each: check_invoice_parties for seller+buyer together, validate_invoice for document rules. It also states the trigger conditions ('use to correct one party's identifiers') rather than leaving usage to inference.

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