Skip to main content
Glama

AICTIONBOT™ Werkbank

Match purchase requisition, purchase order, order confirmation, goods receipt and invoice: 2-way and 3-way match with ready-made queries

match_documents
Read-onlyIdempotent

AICTIONBOT™ Document Match by KULIC Advisory. Compares the documents of one purchase line by line: purchase requisition, purchase order, order confirmation, goods receipt and invoice, in any combination of two or more. Returns the verdicts (requisition, order confirmation, 2-way match, 3-way match), the header fields that differ (order reference, supplier, currency, payment terms, Incoterms, cost centre, approval), per line the quantity, unit price and delivery date of every document with a status, and ready-made queries to the supplier and for internal clarification. Without a purchase order the next best document becomes the reference. Read the fields from the documents yourself and pass them as data; the tool does not read files. Numbers as JSON numbers, dates as YYYY-MM-DD. German keys work too (nummer, bestellbezug, datum, lieferant, waehrung, zahlungsziel, kostenstelle, freigabe, summe, positionen with pos, material, text, menge, einheit, preis, preiseinheit, betrag, liefertermin). With vendor_master the bank details of the invoice are checked as in check_invoice_payment. Deterministic, no AI, nothing stored. 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

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "match_documents"
  }
}

Input Schema

NameRequiredDescriptionDefault
invoiceNoInvoice: number, order_reference, date, supplier, vat_id, iban, currency, payment_terms, total, lines with quantity, price and amount.
languageNoLanguage of the answer. Default de.
tolerancesNoTolerances. Defaults: price 0.5 %, quantity 0 %, delivery date 2 days, order price above the requisition estimate 10 %.
goods_receiptNoGoods receipt or delivery note: number, order_reference, date, lines with the quantity accepted.
vendor_masterNoOptional vendor master rows for the payment check of the invoice: no (vendor number), name, vat_id, iban, country, last_payment (YYYY-MM-DD or null), blocked (bool).
purchase_orderNoPurchase order: number, requisition_reference, date, supplier, currency, payment_terms, incoterms, cost_centre, lines.
order_confirmationNoOrder confirmation from the supplier: number, order_reference, date, supplier, currency, payment_terms, incoterms, lines.
purchase_requisitionNoPurchase requisition (BANF): number, date, supplier wanted, cost_centre, approval, lines with estimated price and wanted delivery date.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations, the description discloses determinism and statelessness ("no AI, nothing stored"), the full output shape (verdicts, differing header fields, per-line quantity/price/delivery date with status, ready-made queries), the effect of the vendor_master payment check, and licensing prerequisites including the free fallback of one check per connection every 30 days. It also sets the fallback reference-document rule, which is genuine behavioural information not present in the annotations.

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 content is dense and largely front-loaded: purpose and document set first, then data-entry rules, then the payment check, then licensing. The opening brand line ("AICTIONBOT™ Document Match by KULIC Advisory") is marketing padding that costs space, and the long single paragraph would read better split by concern, but almost every other sentence carries operative information.

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 complex tool with 8 top-level parameters, five heavily nested document schemas and no output schema, the description still covers what comes back (verdicts, header differences, per-line statuses, ready-made queries), the reference-document fallback, determinism and the licensing gate. Nothing an agent needs in order to decide and call correctly appears to be missing.

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 is 3, but the description adds real meaning: German key aliases (nummer, bestellbezug, lieferant, positionen with pos/menge/preis/liefertermin) that appear nowhere in the schema, the requirement to pass numbers as JSON numbers and dates as YYYY-MM-DD, and the semantics of vendor_master for the invoice bank-detail check. It does not restate the tolerance defaults in detail, which the schema already covers.

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?

The description names a specific verb and resource: compares purchase requisition, purchase order, order confirmation, goods receipt and invoice, line by line, in any combination of two or more. It is clearly distinguishable from siblings such as check_invoice, compare_offers or check_invoice_payment because it states exactly which documents are matched and what verdicts (2-way, 3-way) result.

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?

It states the operating condition (two or more of the five document types, any combination), the handling of a missing purchase order (the next best document becomes the reference) and the key constraint that the agent must read the fields itself because the tool does not read files. It also points to check_invoice_payment as the equivalent behaviour when vendor_master is supplied. It does not explicitly state when to prefer a sibling such as check_invoice or compare_offers instead, which keeps it below a 5.

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.