Skip to main content
Glama

Verify a French invoice

verify_french_invoice
Read-only

Invoice verification for France — use when you HOLD an invoice (or its extracted fields) and must check that the identifiers it displays belong together before paying it. Cross-checks in ONE call: the SIREN against the official registry (existence and active status, live), the VAT number printed on the invoice against the one computed from the SIREN (the French key is deterministic) AND live against VIES, and the IBAN's ISO 13616 form + key digits with the bank identified. Returns a deterministic verdict coherent/incoherent/inverifiable with closed-list reasons traced to their source — flags a VAT number that belongs to ANOTHER company, a ceased supplier, or a key-invalid IBAN. A VIES outage yields inverifiable, never a false invalid. NOT a payee verification: the bank leg checks form only — a valid-but-swapped IBAN is not detectable, and non_verifie says so next to the verdict. At least one of tva/iban is required (a SIREN alone is a profile, not a cross-check). Paid via x402 ($0.02 in USDC or EURC).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tvaNoVAT number printed on the invoice, e.g. FR27552032534 — cross-checked against the SIREN and live against VIES. At least one of tva/iban is required
ibanNoIBAN printed on the invoice (spaces tolerated) — form + key + bank identification, never a holder-name check. At least one of tva/iban is required
sirenYes9-digit SIREN printed on the invoice (digits only)
api_keyNoOptional Sirenic API key (srn_live_…) to pay with prepaid credits instead of x402 — no wallet needed. Get one at https://api.sirenic.eu/compte. Ignored when x_payment is provided (the signed payment wins). On insufficient balance the tool returns a credits error, not an x402 quote.
x_paymentNoOptional signed x402 PAYMENT-SIGNATURE header value. Omit to receive the payment quote.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
hintNoHow to settle the quote, present when payment_required is true.
quoteNoThe signable x402 payment requirements when payment_required is true: {x402Version, accepts[]} where each entry carries scheme, network, amount, asset and payTo (USDC and EURC options at the same numeric amount). Sign one entry and call again with `x_payment`.
resultatNoThe endpoint's JSON response when payment_required is false. Paid responses carry `source`, `disclaimer` and an Ed25519 signature; KYB, batch KYB, sanctions, intelligence and the five invoicing tools (prepare_french_invoice_file, prepare_european_invoice_file, prepare_french_einvoicing_recipient, verify_iban_bank, validate_eu_vat_number) also carry a `provenance` array — one entry per block served, with the official register, licence, version, `as_of` date and `precision_as_of` (what that date means). Codes are documented at GET /v1/provenance/registres (free).
payment_requiredYesTrue when this response is an x402 payment quote instead of data: settle one of the quote's `accepts` options and call the tool again with `x_payment`.

TDQS

A4.7/5.0
Behavior5/5

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

Greatly exceeds the readOnlyHint/openWorldHint annotations by disclosing live-registry behavior, deterministic verdicts, closed-list reasons, VIES-outage handling ('inverifiable, never a false invalid'), and the bank-leg limitation ('valid-but-swapped IBAN is not detectable'). Also explains payment/credits behavior without contradicting the annotations.

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?

Dense but efficient: the purpose is front-loaded, the cross-checks are enumerated compactly, limitations are stated in one clause, and payment mechanics earn their place. No filler or repetition of the title.

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 a multi-parameter verification tool with output schema present, the description covers the use case, required inputs, failure modes, limitations, and billing side effects. An agent has enough context to decide whether to call it and what to expect from the verdict.

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?

The schema already documents all 5 parameters fully, so the baseline is 3. The description adds non-obvious semantics beyond the schema: the French VAT key is deterministic, a SIREN alone is a profile rather than a cross-check, and the api_key failure mode differs from the x402 path ('credits error, not an x402 quote').

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 and resource: verifying that a French invoice's identifiers belong together before payment. Clearly differentiates its combined cross-check scope from single-purpose siblings like validate_eu_vat_number and verify_iban_bank, and explicitly notes what it is not ('NOT a payee verification').

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 an explicit trigger condition ('use when you HOLD an invoice... before paying it'), a clear exclusion ('NOT a payee verification'), and a hard requirement ('At least one of tva/iban is required'). Does not explicitly name the alternative tools, but the scope boundary and 'in ONE call' phrasing make the intended usage clear.

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.

TDQS

A3.6/5.0
Disambiguation2/5

Several French company bundles overlap in purpose (get_french_company_file, get_french_company_kyb_file, get_french_company_intelligence, get_french_company_health_summary) and procurement/competitor tools overlap (get_french_company_public_procurement, get_eu_procurement_awards, get_company_procurement_competitors). Although descriptions try to differentiate, an agent could easily select the wrong tool when looking for a company overview or procurement history.

Naming Consistency4/5

Most tools follow a consistent get_/list_/search_ + country + entity pattern, e.g. get_french_company_profile, list_danish_company_filings, so navigation is predictable. Deviations like check_french_regulator_alerts, suggest_company_names, verify_iban_bank, and the prepare_* verbs are understandable but break the strict verb_noun pattern.

Tool Count1/5

77 tools is excessive for a single server regardless of how broad the domain is; the calibration treats 50+ as an extreme mismatch. While France is well covered and several countries appear, much of the surface is micro-endpoints (list_/get_ filing pairs per country) that could be consolidated.

Completeness3/5

France coverage is impressively complete (identity, financials, legal events, procurement, IP, risk, surveillance, invoicing), and the surveillance lifecycle has create/get/renew/stop. But European coverage is inconsistent: Germany has only insider transactions, Spain only acts, and several major jurisdictions lack accounts/officers/insolvency; an agent expecting 'European company due diligence' will hit dead ends.

Resources