Skip to main content
Glama

FrankKi

by app.frankki
OverviewDiscussionsAdmin

Beleg abrufen

document_get
Read-only

Liefert ein Dokument mit allen Belegdaten (Positionen, Summen, USt-Sätze, Bezug) sowie letterId und orderId des Briefs, in dem es steckt. Das Feld referencePrefill enthält den fertigen references-Block für einen Folgebeleg: übernimm ihn unverändert als document.references in ein document_create für Mahnung, Zahlungserinnerung oder Gutschrift. Unter exports liefert FrankKi für versendete Rechnungen und Gutschriften signierte Download-Links: zugferdPdfUrl ist ein PDF/A-3 mit eingebetteter EN-16931-XML (ZUGFeRD), xrechnungXmlUrl die reine XRechnung-XML. Beide sind zum Herunterladen und Archivieren gedacht; die Übermittlung an ein Portal bleibt bei dir. Fehlt ein Export, nennt das Feld den Grund: DOCUMENT_EXPORT_NOT_READY heißt später erneut versuchen (Versand oder Freischaltung stehen noch aus), DOCUMENT_EXPORT_NOT_SUPPORTED heißt dauerhaft (der Export gilt für Rechnungen und Gutschriften; bei Mahnung und Zahlungserinnerung nutze die Rechnung, auf die sie sich beziehen). Nächster Schritt: order_status verfolgt den Versand, document_create legt mit references eine Mahnung oder Gutschrift dazu an. EN: Returns one document with its full payload (line items, totals, VAT rates, reference) plus the letterId and orderId of the letter it lives in. The field referencePrefill carries the ready-made references block for a follow-up document: paste it unchanged into document.references of a document_create for a dunning letter, payment reminder or credit note. Under exports FrankKi returns signed download links for sent invoices and credit notes: zugferdPdfUrl is a PDF/A-3 with embedded EN 16931 XML (ZUGFeRD), xrechnungXmlUrl the pure XRechnung XML. Both are download-only; transmitting an e-invoice to a portal stays with you. When an export is missing the slot names the reason: DOCUMENT_EXPORT_NOT_READY means try again later (the send or the activation is still pending), DOCUMENT_EXPORT_NOT_SUPPORTED means permanently (the export covers invoices and credit notes; for a dunning letter or payment reminder use the invoice they refer to). Next step: order_status tracks the send, document_create creates a dunning letter or credit note via references.

Input Schema

NameRequiredDescriptionDefault
reasoningNo
documentIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only cover the safety profile (readOnly, non-destructive, closed-world), so the description adds substantial behavioral context: signed export links (ZUGFeRD PDF/A-3, XRechnung XML), that transmission to a portal is the caller's job, and the meaning of DOCUMENT_EXPORT_NOT_READY (retry) vs DOCUMENT_EXPORT_NOT_SUPPORTED (permanent, with the workaround).

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Content is front-loaded and every section is informative, but the entire text is duplicated verbatim in German and English, roughly doubling length without adding meaning. For a single-ID fetch tool this is heavier than necessary.

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?

With no output schema, the description does the work of explaining the return shape, export URLs, error semantics, and follow-up tools, which is thorough. The remaining gap is that neither input parameter is described anywhere.

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

Parameters2/5

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

Schema description coverage is 0% and the description says nothing about documentId (format, source, how to obtain it) or the reasoning field. It explains return payload fields, which are not parameters, so it fails to compensate for the coverage gap.

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 ('Liefert ein Dokument mit allen Belegdaten') and enumerates exactly what is returned: Positionen, Summen, USt-Sätze, Bezug, letterId, orderId. An agent can immediately distinguish this single-document fetch from the sibling document_list.

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 downstream routing: paste referencePrefill unchanged into document_create for Mahnung/Zahlungserinnerung/Gutschrift, and points to order_status for tracking the send. It never explicitly contrasts document_get with document_list, but the usage context is clear.

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

All FrankKi toolsInspect
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