AICTIONBOT™ Werkbank

Check a supplier invoice against order and goods receipt (AICTIONBOT™ invoice check)

check_invoice

Read-only

Needs the user's AICTIONBOT™ Werkbank licence; each call uses one AI analysis from the licence quota. Checks a supplier invoice like an accounts payable clerk doing a three-way match: line by line against the purchase order or contract and the goods receipt (price, quantity, new or missing items), totals and tax, payment term and early payment discount, and for German invoices the mandatory content under § 14 UStG. Returns the lines with status and notes, the mandatory content check and what to clarify before paying. Not tax advice. The texts are processed for this answer only and are not stored by KULIC Advisory.

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": {
      "invoice_text": "<invoice_text>"
    },
    "name": "check_invoice"
  }
}

Input Schema

Name	Required	Description
`language`	No	Language of the answer: de, en, fr, es, pt or zh. Default de.
`invoice_text`	Yes	Text of the invoice.
`goods_receipt`	No	Optional: what was actually received, e.g. quantities per item.
`reference_text`	No	Optional: text of the purchase order or contract to compare against.

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 5, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, non-destructive, openWorld, non-idempotent), and the description adds genuinely useful behaviour: each call consumes one AI analysis from the licence quota, and input texts are not stored. The 'not tax advice' disclaimer and the pre-payment clarification framing further orient the agent.

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?

The licence and quota constraint is front-loaded, followed by the check scope and the return contents, which is a sensible order. It is dense but every clause carries information; only the trailing data-protection sentence is somewhat boilerplate.

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 carries the return-value burden and does so reasonably: lines with status and notes, the mandatory content check, and what to clarify before paying. Combined with 100% schema coverage, an agent has enough to invoke it correctly.

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%, so all four parameters are already documented, including the language enum and text length limits. The description adds a modest mapping by saying the invoice is compared against the purchase order/contract and the goods receipt, but gives no extra syntax or format guidance 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 names a specific verb and resource ('Checks a supplier invoice') and details the three-way-match scope (price, quantity, new/missing items, totals and tax, payment term, § 14 UStG content). It is distinguishable from siblings such as check_invoice_payment or check_price_increase by the breadth of the match, though it never names those alternatives 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?

Usage context is implied by the licence requirement and the three-way-match framing, so an agent can infer this is the full invoice audit rather than a single-field check. However, there is no explicit statement of when to choose this over check_invoice_payment or check_discount_window, and no prerequisites beyond licence ownership.

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

All AICTIONBOT™ Werkbank 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?