Skip to main content
Glama

AICTIONBOT™ Werkbank

Build a category profile from a spend list and contracts: volume, suppliers, concentration, next notice date, levers

build_category_profile
Read-onlyIdempotent

AICTIONBOT™ Category Profile by KULIC Advisory. From your own spend rows and, if present, your contract list it builds one file for a category: total and share of spend, suppliers with their share, concentration, small orders, monthly course, contracts with the last day to give notice, and the levers that follow. Rows without a category get a suggested one from supplier name and text. 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": {
      "spend": "<spend>"
    },
    "name": "build_category_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
spendYesSpend rows: supplier, amount, date (YYYY-MM-DD or DD.MM.YYYY), category (optional), text (optional), document (optional).
todayNoReference date, YYYY-MM-DD. Default today.
categoryNoCategory to profile. Default: the largest category in the data.
languageNoLanguage of the answer. Default de.
contractsNoOptional contracts: supplier, subject, end (date), notice (e.g. 3 months), auto_renewal (yes/no), category.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4/5.0
Behavior5/5

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

Annotations already mark this read-only, idempotent, closed-world and non-destructive, and the description still adds substantive behavior: deterministic processing with no AI, no data retention ('nothing stored'), a fallback that suggests categories for uncategorized rows from supplier name and text, and a precise licensing/auth path including the free-check quota. Those are the details an agent cannot derive from the annotation flags.

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 output inventory is front-loaded and each clause carries real information about what the file contains. The opening brand line ('AICTIONBOT™ Category Profile by KULIC Advisory') and trademark styling are pure boilerplate overhead in an otherwise dense, purposeful 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?

With no output schema, the description correctly takes on the burden of describing the result by listing every section of the profile. It also covers auth, determinism, and data handling. The main remaining gap is the artifact itself: 'one file' never specifies format (xlsx/csv/pdf) or how it is returned or downloaded, which an agent needs to relay to a user.

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; the description earns an extra point by explaining behavior the schema cannot: that uncategorized spend rows receive a suggested category derived from supplier name and text, so the 'category' parameter interacts with data-derived defaults rather than failing on missing values. It also clarifies that contracts are optional and only used 'if present', which frames the default-category logic.

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 ('builds') and resource ('one file for a category') and enumerates the exact contents: spend totals and share, supplier shares, concentration, small orders, monthly course, contract notice dates, and levers. An agent knows precisely what artifact it receives. It never names a sibling such as analyse_spend or calculate_notice_deadline, so differentiation relies on the reader inferring overlap from the output list.

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 is implied rather than stated: it is the tool for when you have spend rows (and optionally contracts) and want a per-category profile. Access conditions are given ('Needs sign-in', licence or one free check per connection every 30 days), which is useful context. There is no explicit when-not guidance and no routing to the closely overlapping siblings (analyse_spend, check_contracts, calculate_notice_deadline).

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.