Skip to main content
Glama

AICTIONBOT™ Werkbank

Analyse a spend or order export: who carries the volume, small orders, bundling, tail and possible duplicate postings

analyse_spend
Read-onlyIdempotent

AICTIONBOT™ Spend Cube by KULIC Advisory. Takes the rows of a spend, invoice or order export and returns total volume, documents and suppliers, how many suppliers carry 80 % of the volume, the top 10 suppliers with their share, volume by category with a suggested category where none is given, small orders under a threshold, rows without an order number, possible duplicate postings, categories bought from three or more suppliers (bundling) and the tail X-ray: who carries the last 5 % of volume, one-time suppliers and a suitable channel per category. Column names in German or English are recognised. 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

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": {
      "rows": "<rows>"
    },
    "name": "analyse_spend"
  }
}

Input Schema

NameRequiredDescriptionDefault
rowsYesSpend rows as objects: supplier (Lieferant) and amount (Betrag, net) are required; date (Datum), category (Warengruppe), order_no (Bestellnummer) and description (Beschreibung) are optional.
languageNoLanguage of the answer. Default de.
small_order_thresholdNoSmall order threshold in EUR. Default 250.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the description does not need to restate safety. It adds genuinely new context: deterministic with no AI, nothing stored, German/English column-name recognition, and a licensing gate with a limited free mode ('one check per connection every 30 days'). It stops short of describing output structure or what happens to malformed rows, but the extra context is substantial.

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 output enumeration is justified because there is no output schema, but it is delivered as one very long sentence that is hard to parse, and it opens with branding ('AICTIONBOT™ Spend Cube by KULIC Advisory') that earns no selection value. The licence paragraph is useful but tacked on rather than structured.

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 thoroughly, covering volume, Pareto suppliers, top-10 shares, category suggestions, threshold orders, missing order numbers, duplicates, bundling and tail analysis. Access requirements are also covered, leaving only minor gaps such as error behavior on invalid rows.

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 three parameters (rows, language, small_order_threshold) are already documented with defaults and constraints. The description only echoes the threshold concept ('small orders under a threshold') and adds the German/English column-name tolerance, which is modest value 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 specific verb and resource ('Takes the rows of a spend, invoice or order export and returns total volume, documents and suppliers...') and enumerates the concrete analyses produced. It does not reference any sibling tool by name, so an agent cannot use it to distinguish this from neighbours such as check_kpis or atlas_overview.

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 input shape ('rows of a spend, invoice or order export') and by the licensing note, but there is no explicit when-to-use/when-not guidance and no named alternative for related spend questions. The licence and free-check framing is helpful but concerns access, not tool selection.

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.