Skip to main content
Glama

Aidoptio: AI adoption catalog, estimates and advisor tools

EU AI Act and agent risk triage

ai_act_triage
Read-onlyIdempotent

Five questions about one AI use or agent. Returns an indicative risk tier under Regulation (EU) 2024/1689 (prohibited, high-risk, transparency, minimal), whether agent risk is high, the deadlines that apply, the controls to put in place and first steps, with the EUR-Lex source and the date the status was last checked. Same rule set as the triage on aidoptio.com. Indicative triage, not legal advice. Deterministic: no model is called and the answers are not stored.

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": {
      "domain": "<domain>",
      "autonomy": "<autonomy>",
      "data": "<data>",
      "role": "<role>",
      "maturity": "<maturity>"
    },
    "name": "ai_act_triage"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataYesData processing and origin none = No personal data; eea = Standard business data and personal data within the EEA; sensitive = Special category data or customer data outside the EEA.
langNoLanguage of the returned text: en (English, default) or nl (Dutch).en
roleYesYour organisation's role under the EU AI Act deployer = Deployer of existing models or tools; provider = Provider, or substantial modification or fine-tuning under your own brand.
domainYesApplication domain and impact on people prohibited = Manipulation, social scoring or emotion recognition at work; high = Recruitment, credit, life or health insurance, education, essential services, critical infrastructure; transparency = Chatbot or generated content facing customers or citizens; minimal = Internal knowledge search or writing assistant.
autonomyYesDegree of autonomy of the system or agent draft = Draft proposal for an employee only; autonomous = Independently executes external actions or transactions via tools or MCP.
maturityYesCurrent assurance and AI literacy (Art. 4) solid = Role training, AI register, DPIA and kill switch in place; partial = Partly: policy or training, but no complete register or test; adhoc = Still ad hoc.

Output Schema

NameRequiredDescriptionDefault
tierYes
rulesNo
sourceYes
answersNo
controlsYes
deadlinesYes
next_stepNo
tier_textNo
agent_highYes
disclaimerYes
tier_labelYes
first_stepsYes
status_checkedNo
disclosures_urlNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already cover readOnly, idempotent, non-destructive, closed-world behavior, and the description adds substantive context beyond that: deterministic execution with no model called, answers not stored, indicative rather than legal advice, and EUR-Lex sourcing with a last-checked date. The only gap is that it doesn't describe response size or how the deadline/control lists are scoped.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with what the tool does and returns, followed by the caveat and determinism note; each sentence carries distinct information with no repetition of the schema or title.

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?

An output schema exists, yet the description still usefully summarizes what comes back (tier, agent-risk flag, deadlines, controls, source, last-checked date) and covers the legal-advice boundary and data handling. For a self-contained triage tool this is close to complete; only the shape of the returned controls/deadlines is left implicit.

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% with all six parameters as documented enums, so the schema does the heavy lifting and baseline 3 applies. The description's 'Five questions' framing maps to the five required inputs and tells the agent each parameter is a discriminating triage answer, but adds no format or value detail beyond the schema.

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?

States a specific verb and resource ('Five questions about one AI use or agent... Returns an indicative risk tier under Regulation (EU) 2024/1689') and enumerates the four possible tiers plus the additional outputs. An agent can distinguish this triage/classification tool from siblings like ai_literacy_scan or verify_ai_text without opening the schema.

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?

'Five questions about one AI use or agent' sets clear scope: a single use case per call, scoped to EU AI Act classification, with the 'not legal advice' framing signalling when this is appropriate. It does not name explicit alternatives or when-not-to-use conditions, so it falls short of 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.

Resources