Skip to main content
Glama

AICTIONBOT™ Werkbank

Invoice letter: a letter to suppliers with the company's invoice requirements, purchase order number, e-invoice format and payment terms, in German and English

write_invoice_letter
Read-onlyIdempotent

AICTIONBOT™ invoice letter by KULIC Advisory (tool 48), built on the Execution Toolkit templates T24 (data self-audit) and T05 (process improvement). Takes the company's details (name, address, VAT ID, invoice mailbox, whether a purchase order number is required, payment terms, contact) and writes a letter to suppliers in German and English with the mandatory invoice details, the purchase order number rule, the e-invoice format (XRechnung or ZUGFeRD from the EN 16931 profile, as of November 2026 receiving is mandatory in Germany, sending phases in by 2027 and 2028) and where to send. Plus a checklist for the company. Not legal or tax advice. Deterministic, no AI, nothing stored, nothing sent. 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": {
      "company": "<company>"
    },
    "name": "write_invoice_letter"
  }
}

Input Schema

NameRequiredDescriptionDefault
vat_idNoVAT ID of the company.
addressNoInvoice address.
companyYesCompany name.
contactNoContact for questions.
languageNoLanguage of the answer. Default de.
po_requiredNoIs a purchase order number required on every invoice? Default yes.
invoice_emailNoMailbox for invoices.
payment_termsNoPayment terms, for example "30 days net, 2 % within 10 days".

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior5/5

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

Annotations already mark this as read-only, idempotent, non-destructive and closed-world, and the description adds substantial context on top: deterministic, no AI, nothing stored, nothing sent, no legal or tax advice, plus an explicit licence requirement and a described free tier of one check per connection every 30 days. Those are exactly the operational facts an agent cannot get from structured fields.

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?

The core content is dense but relevant; however, the opening is loaded with branding and provenance (AICTIONBOT™, 'tool 48', templates T24 and T05) that does not help an agent decide or invoke. The e-invoice date narrative (November 2026, 2027/2028 phases) is background rather than actionable. The purpose would be better front-loaded before the licence paragraph.

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 an eight-parameter, no-output-schema tool, the description is nearly complete: it names the artifacts produced (bilingual letter plus checklist), the domain constraints (XRechnung/ZUGFeRD, EN 16931), and the access model. Only the relationship to sibling invoice tools and default behaviour for optional inputs is left unaddressed, and the schema covers defaults.

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

Parameters3/5

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

Schema description coverage is 100% and all eight fields carry their own descriptions, so the schema does the heavy lifting. The description enumerates the same inputs (name, address, VAT ID, mailbox, PO requirement, payment terms, contact) and adds the useful detail that the PO rule is applied inside the letter, but contributes no format or constraint detail beyond 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 states a concrete verb and artifact: it writes a supplier-facing invoice-requirements letter in German and English, with the PO-number rule, e-invoice format and payment terms, plus an internal checklist. That is far more specific than the title alone. It does not, however, contrast itself with neighbouring tools such as check_einvoice, so an agent must infer the boundary itself.

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

Usage Guidelines2/5

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

There is no explicit when-to-use or when-not-to-use guidance and no alternative tool is named. The reader can infer this is the setup step for supplier invoice requirements, but nothing states that check_einvoice validates invoices rather than drafting a letter. The only conditional content is licensing/access, which is not usage guidance.

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.