Skip to main content
Glama

Screen confirmed facts for the EU AI Act

merron_screen_ai_act
Read-onlyIdempotent

Run Merron's versioned, bounded AI Act rules on facts the user has explicitly confirmed. Returns a conditional screening result, unresolved routes, missing questions and official references. Never infer confirmation or legal compliance from source code or absence of signals. Unknown answers remain unknown. This computation does not check documents, use an AI model, save a report, access accounts or certify compliance.

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": {
      "factsConfirmedByUser": "<factsConfirmedByUser>",
      "facts": "<facts>"
    },
    "name": "merron_screen_ai_act"
  }
}

Input Schema

NameRequiredDescriptionDefault
factsYes
factsConfirmedByUserYesTrue only after the user confirms the supplied answers describe the actual system.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • addedInput schema / properties / facts / propertyNames
      Added value: +{
      +  "type": "string"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / facts / additionalProperties / anyOf
      Previous value: -[
      -  {
      -    "type": "boolean"
      -  },
      -  {
      -    "enum": [
      -      "provider",
      -      "deployer",
      -      "both"
      -    ],
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]New value: +[
      +  {
      +    "type": "boolean"
      +  },
      +  {
      +    "enum": [
      +      "provider",
      +      "deployer",
      +      "both"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "enum": [
      +      "high_risk",
      +      "not_high_risk_6_3",
      +      "not_stated"
      +    ],
      +    "type": "string"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / factsConfirmedByUser / description
      Previous value: -"True only after the user confirms the supplied answers describe the actual product."New value: +"True only after the user confirms the supplied answers describe the actual system."
  4. First observed

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description does add the shape of the response (conditional result, unresolved routes, missing questions, official references), but with no output schema the remaining gap is that it does not explain what 'unresolved routes' or 'missing questions' actually contain, so the added context is useful but thin.

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?

Front-loaded with the action and the return shape, then a compact block of exclusions. The disclaimer list is dense but each clause rules out a concrete misreading, so little is wasted; the only slack is that 'does not certify compliance' partly repeats 'never infer legal compliance'.

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?

For a two-parameter, no-output-schema tool, the description covers the preconditions, the nature of the result and the negative scope well. What it still lacks is a description of the keys and value semantics for the facts payload, which an agent needs before it can call the tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 50%, and the whole burden sits on factsConfirmedByUser, which is already documented by const:true. The core facts object — a nested map whose keys are arbitrary strings and whose values are booleans, roles, risk levels or null — gets no explanation of what keys to supply or how answers map to legal questions. 'Unknown answers remain unknown' hints that null is legitimate, but nothing tells the agent how to construct this payload, so the description does not compensate for the coverage gap.

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?

A specific verb-plus-resource statement: it runs versioned, bounded AI Act rules over user-confirmed facts and returns a conditional screening result. The description also marks out its boundaries against sibling capabilities like document checking or model inference, so an agent can tell this apart from merron_scan_project or merron_get_questions.

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?

It states the precondition for use: the facts must have been explicitly confirmed by the user, and it warns never to infer confirmation or legal compliance. It also rules out adjacent tasks (checking documents, using an AI model, saving a report), but it never names a sibling tool as the alternative to use instead, so routing still relies on the agent's own inference.

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.

Resources