Skip to main content
Glama

MaxRechnung

ZUGFeRD 2.5.2 / Factur-X 1.09.2 (PDF/A-3 mit eingebettetem XML)

download_invoice_zugferd
Read-only

Tarif: in jedem Tarif (Free, Pro, Business).

ZUGFeRD 2.5.2 / Factur-X 1.09.2 (PDF/A-3 mit eingebettetem XML)

Das Rechnungs-PDF als PDF/A-3 (ISO 19005-3) mit eingebettetem CII-XML (factur-x.xml) nach ZUGFeRD 2.5.2 / Factur-X 1.09.2. Profil je Rechnung: BASIC, EN 16931 (COMFORT, Vorgabe) oder EXTENDED. Mit Accept: application/json: { filename, warnings }. Gegen den Mustang-Validator (veraPDF + Profil-Schematron) geprüft; abwärtskompatibel bis ZUGFeRD 2.0.1 (BMF-Untergrenze § 14 UStG). Das eingebettete XML wird beim Festschreiben eingefroren.

Asynchron. Die Wandlung läuft in einer Warteschlange; bereits erzeugte Dateien kommen sofort (Cache nach Inhalt, festgeschriebene Belege werden beim Festschreiben vorab erzeugt). Ist die Datei nicht binnen wait Sekunden fertig, antwortet der Endpunkt mit 202 + Job-Objekt und Location: /api/v1/jobs/{id} — dort pollen oder auf das Webhook-Event invoice.zugferd_ready warten, danach diesen Endpunkt erneut abrufen. Höchstens 100 offene Aufträge je Konto (sonst 429).

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": {
      "id": "<id>"
    },
    "name": "download_invoice_zugferd"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesInterne `id` der Rechnung (UUID), nicht die Belegnummer. Zu einer Nummer (z. B. `RE-2026-0004`) liefert `GET /invoices?number=…` (MCP: `list_invoices` mit `number`) die `id`.
waitNoSekunden, die der Aufruf auf die fertige Datei wartet, bevor er mit 202 antwortet (0–60, Vorgabe 30).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnlyHint/destructiveHint=false, so the description's real contribution is the async contract: queue-based conversion, content-addressed caching, immediate return of already-generated files, 202 + job object + Location header when `wait` elapses, a 100-open-job-per-account cap returning 429, and the fact that the embedded XML is frozen at finalization. It also discloses validation (veraPDF + profile Schematron) and backward compatibility to ZUGFeRD 2.0.1. Only the `Accept: application/json` response shape is thin, but that is covered as well.

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?

Structure is sensible — format definition first, then the async/job mechanics, then limits — and each sentence carries operational information. It is long for a two-parameter tool, and the leading pricing-tier line ("Tarif: in jedem Tarif") is the weakest contributor, but nothing is redundant with the schema.

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-parameter, no-output-schema tool with non-trivial async behavior, the description covers the return path (binary PDF or `{ filename, warnings }` under Accept: application/json), the deferred-job path, the webhook alternative, and the rate-limit failure mode. An agent has enough to invoke it and handle every documented outcome.

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 would be 3, but the description adds real meaning: it explains that `wait` is the timeout before the endpoint falls back to a 202 job response, and clarifies the asynchronous consequences of choosing a short timeout. The `id` parameter is left entirely to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names the concrete artifact produced: an invoice PDF/A-3 (ISO 19005-3) with an embedded CII XML (`factur-x.xml`) per ZUGFeRD 2.5.2 / Factur-X 1.09.2, including the profile variants. That is specific enough to separate it from `download_invoice_pdf` and `download_invoice_xrechnung` on format grounds, though neither sibling is named explicitly.

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

Usage Guidelines3/5

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

It explains the operational conditions (profile per invoice, `wait` budget, what to do after a 202: poll the Location job or wait for the `invoice.zugferd_ready` webhook, then re-call this endpoint). What is missing is explicit routing guidance — when to prefer this over the plain PDF or XRechnung variants, or which profile a caller should expect.

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