Skip to main content
Glama

AICTIONBOT™ Werkbank

Check a planned AI use case for completeness and control: card, data readiness, risk questions, controls, signal proceed, pilot, redesign or stop

check_ai_use_case
Read-onlyIdempotent

AICTIONBOT™ AI use case check by KULIC Advisory, built on the Execution Toolkit template T27 (AI use case governance). Takes the use case card (problem, decision supported, expected value, users, accountable owner, human oversight, success metric, fallback without AI), data readiness ratings 1 to 5 (availability, quality, access, freshness, history), yes or no answers to five risk questions (personal data, decisions about people, external effect, money moves, explainability) and the planned controls with owner and status. Returns what is missing, data readiness, open controls, notes where impact is high and oversight low, and a signal following the template rule: proceed only when data, controls and ownership are clear, otherwise pilot, redesign or stop. Checks completeness and controllability; it is not a legal classification, for example under the EU AI Act. 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_ai_use_case"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoRatings 1 to 5: availability, quality, access, freshness, history.
ownerNo
risksNoyes or no: personal_data, decisions_about_people, external_effect, money_moves, explainability.
usersNo
valueNo
problemNo
controlsNoControls: control, owner, status.
decisionNo
fallbackNo
languageNoLanguage of the answer. Default de.
success_metricNo
human_oversightNolow, medium or high.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive and closed-world, and the description still adds substantive behaviour: deterministic, no AI in the loop, nothing stored, licence-gated with a stated free quota per connection. It also discloses the decision rule that produces the output signal (proceed only when data, controls and ownership are clear, otherwise pilot/redesign/stop), so an agent can anticipate the result rather than treating it as opaque.

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?

Structure is front-loaded: what the tool takes, what it returns, the governing rule, then the caveat and access terms. Most sentences carry distinct information, though the branded opening and the partially restated 'checks completeness and controllability' sentence add some padding for a description this long.

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 12-parameter, nested-input tool with no output schema, the description covers inputs, the shape of the returned findings, the decision rule behind the signal, the scope limit and the access requirements. An agent has everything needed to decide whether to call it and how to fill the payload.

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 description coverage is only 42% across 12 parameters including nested objects, so the description has to compensate, and it largely does: it enumerates the card fields (problem, decision, value, users, owner, oversight, success metric, fallback), expands the ratings object into availability/quality/access/freshness/history on a 1-5 scale, names the five yes/no risk keys, and defines each control as control/owner/status. It adds little about the `language` default or optionality, which the schema handles, so it misses a perfect 5.

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: it checks a planned AI use case card and returns gaps, readiness, open controls and a proceed/pilot/redesign/stop signal. It is far more specific than the title alone and lists the exact input artefacts it consumes. It stops short of 5 because it never distinguishes itself from the near-neighbour sibling ai_readiness, leaving overlap to inference.

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?

Usage context is clear: for a *planned* AI use case, at card-completeness stage, with an explicit exclusion ('it is not a legal classification, for example under the EU AI Act'). The licensing/sign-in path ('Connect without a licence', one check per connection every 30 days) tells the agent what to expect on auth failure. It does not name an alternative tool for the legal-classification job it disclaims, so not 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.