Factur-X: Generate & Validate E-Invoices

Check seller and buyer together

check_invoice_parties

Read-onlyIdempotent

Check a supplied seller AND buyer together, returning combined readiness and separate evidence.

Use before generate_invoice; use check_party for one party and validate_invoice for document rules.
Each party needs siren, siret or vat; siret wins over siren. French identifiers or country_code=FR
require SIREN/SIRET; a French lookup can derive omitted vat. Address fields activate address checks.
requester_vat applies to both lookups but cannot replace either party's vat. Roles follow seller/buyer
argument names; no invoice lines or full invoice body is needed.

Makes at most two EU Verify requests with the caller's plan key; Pro/Scale enable register access.
Returns status and parties.seller/buyer, each with status, reasons and available evidence. Only two
positive results yield invoice_ready; any not_ready yields not_ready, otherwise inconclusive.
Inspect both results: denied plans, invalid input, quotas and outages never establish readiness.
No document quota is consumed; upstream limits still apply per lookup. Results may change on retry.
No invoice is generated, stored or sent.

Input Schema

TableJSON Schema

Name	Required	Description
`buyer`	Yes	Buyer's registry identifiers and optional checks.
`seller`	Yes	Seller's registry identifiers and optional checks.
`requester_vat`	No	Your VAT number for VIES request evidence.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 3, 2026
- addedInput schema / properties / buyer / type
```
Added value: +"object"
```
- addedInput schema / properties / seller / type
```
Added value: +"object"
```
AddedSep 27, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already cover safety (readOnly, idempotent, openWorld), and the description adds substantial operational detail beyond them: at most two EU Verify requests, plan-key usage, Pro/Scale register access, no document quota consumed, upstream per-lookup limits, results may change on retry, and that no invoice is generated/stored/sent.

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 usage, then behavior; every sentence carries information. It is dense and long, but the density is justified by the tool's complexity rather than padding.

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 two-party verification tool with a nested schema and an output schema, the description covers inputs, precedence, request semantics, and the readiness decision logic (two positives yield invoice_ready; any not_ready yields not_ready; otherwise inconclusive) including how denied plans/quotas/outages factor in. Nothing essential is missing.

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

Parameters5/5

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

Schema coverage is 100% (baseline 3), but the description adds real precedence and derivation logic absent from the schema: siret wins over siren, French identifiers/country_code=FR require SIREN/SIRET, a French lookup can derive omitted vat, address fields activate address checks, and requester_vat cannot replace either 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+resource scope ('Check a supplied seller AND buyer together, returning combined readiness and separate evidence') and implicitly contrasts with its sibling check_party by emphasizing the paired scope. An agent can distinguish it from single-party and document-rule tools 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?

Explicitly routes the caller: 'Use before generate_invoice; use check_party for one party and validate_invoice for document rules.' It names both alternatives and the conditions that select them, leaving nothing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Factur-X: Generate & Validate E-Invoices tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?