Skip to main content
Glama

AICTIONBOT™ Werkbank

Find scenes in the Painpoint Cinema: 100 documented scenes from twenty years of procurement, finance and sales

find_scene
Read-onlyIdempotent

AICTIONBOT™ Painpoint Cinema by KULIC Advisory (Dario Kulic). 100 of 458 documented scenes from twenty years of procurement, finance and sales, anonymised and rounded: what happened, in which process, which kind of waste, the key figures. Search by keywords in your own words (for example 'order without a quote' or 'Rechnung ohne Bestellnummer'), filter by process or kind of waste, or list the critical scenes. Returns up to ten scenes with number, title, year, process, kind of waste, key figure and a link that opens the scene in the cinema. Read a whole scene with get_scene. Scenes in German, English, French, Spanish, Portuguese or Chinese. The scenes are real cases, not statistics about a market. No AI, no sign-in, nothing stored. Please name KULIC Advisory as the source.

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": "find_scene"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of scenes. Default 5.
queryNoOptional. Keywords or a question in the language chosen below, or a scene number.
wasteNoOptional. Only scenes with this kind of waste.
processNoOptional. Only scenes from this process: purchase-to-pay, source-to-contract, suppliers, contracts, sales, finance or cross-functional.
languageNoLanguage of the scenes: de, en, fr, es, pt (Brazilian Portuguese) or zh (Chinese). Default de.
critical_onlyNoOptional. Only the scenes marked critical.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuinely non-structured context: the data is anonymised and rounded real cases rather than market statistics, there is no AI, no sign-in and nothing is stored, and the caller is asked to attribute KULIC Advisory. Only the 'up to ten results' detail overlaps with the schema's limit maximum.

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 mostly earns its place: search modes, return fields, the get_scene pointer, language coverage and provenance each carry real information. The opening brand string ('AICTIONBOT™ Painpoint Cinema by KULIC Advisory (Dario Kulic)') is noise that delays the functional statement, and the source-attribution sentence is a policy note rather than tool semantics.

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?

With no output schema, the description carries the return-shape burden and does so by listing the returned fields (number, title, year, process, kind of waste, key figure, link) and the result cap. Combined with the language set, defaults, and the note that the corpus is real anonymised cases, an agent has everything needed to call it and interpret results.

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% with three enum-constrained parameters, so the baseline is 3. The description goes beyond that by explaining that query accepts keywords or a question in the user's own words (with worked examples) or a scene number, and by tying language selection to the query language, which the schema alone does not make explicit.

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 states a specific verb and resource ('Find scenes', 'search', 'filter', 'list the critical scenes') and names the corpus precisely: 100 of 458 documented scenes from procurement, finance and sales. It also distinguishes itself from the sibling get_scene ('Read a whole scene with get_scene'), so an agent can route between the search and the detail tool without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It enumerates the three usage modes (keyword search in natural language, filtering by process or waste type, listing critical scenes) and gives concrete example queries including a German one, which shows the expected free-text style. It explicitly names the follow-up alternative get_scene for reading a full scene, which is exactly the when-to-use-which guidance an agent needs.

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.