Skip to main content
Glama

AICTIONBOT™ Werkbank

Write an invoice: German e-invoice as ZUGFeRD/Factur-X EN 16931 or XRechnung 3.0 (CII XML), with the mandatory details checked under section 14 UStG

create_einvoice
Read-onlyIdempotent

AICTIONBOT™ invoice writer by KULIC Advisory (tool 52). Takes seller, buyer, invoice number and dates, payment terms and lines (description, quantity, UN/ECE unit code, net unit price, VAT rate or category) and returns a structured e-invoice as UN/CEFACT Cross Industry Invoice XML: ZUGFeRD/Factur-X profile EN 16931 or XRechnung 3.0 for German public authorities (Leitweg-ID as buyer_reference). Calculates in cents (line amounts, VAT per category and rate, totals), checks the mandatory details of section 14 (4) UStG, the EN 16931 business rules and the German XRechnung rules (BR-DE: contact, phone, e-mail, IBAN, buyer reference), validates IBAN check digits and VAT ID format, and handles small business (section 19 UStG), reverse charge (section 13b UStG), intra-community supply and export with the exemption reason. Red findings block the XML, yellow ones are notes. The Workbench page https://www.kulicadvisory.com/workbench/write-invoice/ turns the same data into a PDF/A-3 with the XML embedded. Generated invoices passed XSD, the official EN 16931 and KoSIT XRechnung schematron and veraPDF. Deterministic, no AI, nothing stored. Not tax advice. Needs sign-in: runs with an AICTIONBOT™ Werkbank licence; without a licence one check per connection every 30 days is free (sign in with “Connect without a licence”).

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": {
      "lines": "<lines>"
    },
    "name": "create_einvoice"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoFree note on the invoice
buyerNoname, street, postcode, city, country, vat_id, email
linesYesRows: description, quantity, unit (C62 piece, HUR hour, DAY, MON, KGM, MTR, MTK, LTR, KMT, LS lump sum, SET), unit_price (net), vat_rate (19, 7), category (standard, small_business, reverse_charge, intra_community, export, not_taxable).
numberNoInvoice number
sellerNoname, street, postcode, city, country (ISO code, default DE), vat_id, tax_number, register, email, phone, contact, iban, bic, account_holder
profileNozugferd (default, EN 16931) or xrechnung (XRechnung 3.0, for public authorities)
currencyNoISO currency code. Default EUR.
due_dateNoDue date
languageNoLanguage of the answer. Default de.
issue_dateNoInvoice date YYYY-MM-DD or DD.MM.YYYY
period_endNo
period_startNo
delivery_dateNoDelivery or service date (or use period_start and period_end)
payment_termsNoPayment terms text, for example "Payable within 14 days without deduction."
buyer_referenceNoBuyer reference; for XRechnung to authorities the Leitweg-ID (required for xrechnung)
order_referenceNoCustomer order number

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/idempotentHint/non-destructive, and the description adds materially: nothing is stored, no AI is involved, arithmetic is done in cents, and findings are color-coded with red ones blocking XML generation while yellow ones are notes. It also discloses the licence/sign-in requirement and the validation suite the output has passed (XSD, EN 16931 and KoSIT schematron, veraPDF). That is exactly the behavioral context annotations cannot carry.

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?

Purpose is front-loaded and most sentences carry real information, but the block is dense and includes promotional and incidental material: the trademarked product name, 'tool 52', the full Workbench URL, the 'Not tax advice' disclaimer and the certification list. These could be trimmed or moved without losing guidance the agent needs to call the tool.

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?

For a 16-parameter tool with nested seller/buyer objects and no output schema, the description covers the return artifact (CII XML, profile-dependent), the arithmetic and validation performed, and the blocking-versus-note outcome. It does not say what the caller actually receives when red findings block generation (a list of findings, an error, partial output), which is the one operational gap for a tool with no output schema.

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?

With 88% schema coverage the baseline is 3, but the description goes further by explaining what the parameters mean legally: buyer_reference is the Leitweg-ID and is required for xrechnung, the category values map to §19 small business, §13b reverse charge, intra-community supply and export with exemption reasons, and units must be UN/ECE codes. This adds interpretation the schema's field blurbs do not supply.

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 artifact: it takes seller/buyer/lines data and returns a UN/CEFACT Cross Industry Invoice XML, in either ZUGFeRD/Factur-X EN 16931 or XRechnung 3.0. That is clearly distinguishable from siblings such as check_einvoice (validation) and write_invoice_letter (a letter), so an agent can pick it 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 Guidelines4/5

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

Gives concrete selection context: use profile 'xrechnung' for German public authorities with a Leitweg-ID, 'zugferd' otherwise, and points to the Workbench page when an embedded PDF/A-3 is needed instead of raw XML. It also spells out the access model (licence required, one free check per 30 days). It never explicitly names an alternative tool such as check_einvoice for validating an invoice that already exists, so it stops short of full when/when-not routing.

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.