Skip to main content
Glama

AICTIONBOT™ Werkbank

X-ray a vendor master list: duplicates, invalid IBAN and VAT ID, gaps, dormant vendors and risk signals

check_vendor_master
Read-onlyIdempotent

AICTIONBOT™ Vendor Master X-ray by KULIC Advisory. Takes a vendor (creditor) master list and returns duplicate groups with the reason and a suggested leading record, risk signals (one IBAN under two names, one VAT ID or tax number under two names, bank country different from the country of residence, BIC not matching the IBAN), format errors (IBAN check digits and length, VAT ID format per country and the German check digit, postcode, e-mail, BIC, date), gaps in required fields, dormant vendors without activity and a clean-up list with a proposal per record. Column names in German or English are recognised (Kreditor, Name, Straße, PLZ, Ort, Land, USt-IdNr., Steuernummer, IBAN, BIC, E-Mail, Telefon, Letzte Bewegung, Sperre; no, name, street, zip, city, country, vat_id, tax_number, iban, bic, email, phone, last_activity, blocked). Check digits and formats do not prove that an account belongs to the supplier. Up to 1,000 vendors per call; larger lists run in the browser tool on the user's own device. 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": "check_vendor_master"
  }
}

Input Schema

NameRequiredDescriptionDefault
csvNoAlternative to rows: the list as CSV or tab-separated text. The first line is the header.
rowsNoThe vendor master as rows: one object per vendor, column name to value. The name is required. Up to 1,000 vendors per call.
as_ofNoReference date for dormant vendors, YYYY-MM-DD. Default today.
limitNoEntries shown per section in the text. Default 10.
languageNoLanguage of the answer. Default de.
dormant_monthsNoMonths without activity from which a vendor counts as dormant. Default 24.
similarity_thresholdNoName similarity from which two records count as duplicates. Default 0.88.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, and the description adds materially more: deterministic with no AI, nothing stored, licence requirement with a free 30-day allowance, a hard 1,000-vendor cap, and a caution that valid check digits do not prove account ownership. Those are decision-relevant traits not present in any structured field.

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?

Purpose and output inventory are front-loaded, followed by input recognition, limits and licensing in a defensible order. The long parenthetical alias lists and the licence paragraph are dense, but each carries information an agent needs to format input or anticipate failure.

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 seven optional parameters, no output schema and a broad analysis output, the description still explains results, input aliases, limits and access conditions. Only minor gaps remain, such as how results are structured per section or what an empty/failed run returns.

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 by listing the recognised German and English column aliases (Kreditor/name, USt-IdNr./vat_id, Letzte Bewegung/last_activity), which tells the agent what content csv and rows must contain. It does not clarify as_of, limit or similarity_threshold beyond the schema, so not a 5.

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 ('X-ray a vendor master list') and enumerates exactly what the check returns: duplicate groups with a suggested leading record, risk signals, format errors, field gaps, dormant vendors and a clean-up list. An agent can tell this apart from list-hygiene siblings like find_in_list or audit_list without opening a 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 clear context for invocation: input is a creditor master, up to 1,000 vendors per call, larger lists must use the browser tool instead — an explicit scope boundary. It also explains the licence/sign-in prerequisite. It does not name a sibling alternative (e.g. screen_supplier_risk) or state when not to use it, so it stops short of 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.