Skip to main content
Glama

Fidget Labs

Classify EU AI Act risk

classify_eu_ai_act_risk
Read-onlyIdempotent

Classify how an organization builds or uses AI against the risk tiers of the EU AI Act (Regulation (EU) 2024/1689). Returns the highest tier triggered, every tier with whether it applies, the compliance deadline and maximum penalty for each, whether the organization leans provider or deployer, and which specific answers drove the result.

Every parameter's description is the question as a person is asked it, and its enum is the permitted values. Ask the person the questions rather than guessing: a wrong answer to the Annex III domains or the prohibited practices list changes the tier.

Results are informational and not legal advice. Relay the disclaimer field with any answer built from this.

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": {
      "size": "<size>",
      "industry": "<industry>",
      "role": "<role>",
      "transparencyInteraction": "<transparencyInteraction>",
      "transparencyContent": "<transparencyContent>",
      "roleSignal": "<roleSignal>",
      "aiFrequency": "<aiFrequency>",
      "annexDomains": "<annexDomains>",
      "biometricUse": "<biometricUse>",
      "prohibited": "<prohibited>"
    },
    "name": "classify_eu_ai_act_risk"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleYesWhat is your role?
sizeYesHow large is your organization?
industryYesWhat industry are you in?
prohibitedYesCould any of your AI uses fall into these categories? These are uses the EU has banned outright. Most businesses will select none. Select any you are unsure about. Selecting one is not a verdict. It flags something worth an urgent closer look.
roleSignalYesWhich best describes how your business gets the AI it uses? This is about where your AI comes from, not how it works. 'Building or heavily customizing' means your team trains, fine-tunes, or substantially modifies AI models. 'Using tools others built' means you use AI products or features made by other companies, roughly as they come.
aiFrequencyYesHow often does your business use AI? Including internal tools. Count anything where AI helps with analysis, drafting, scheduling, coding, research, or any task, even if customers never see it.
annexDomainsYesDoes AI help make or influence any decisions about people in your business? Select any that apply. This is about decisions that meaningfully affect a person, where AI plays a role in the outcome.
biometricUseYesDoes your business use AI that recognizes or analyzes people's physical characteristics? For example, systems that identify people by face or voice, or that analyze physical or biometric characteristics.
industryOtherNoFree text naming the industry. Only meaningful when `industry` is "other".
transparencyContentYesDoes your business use AI to create or edit content that you publish or send out? For example, marketing copy, social posts, product descriptions, images, audio, or video where AI created or significantly changed what you publish or send.
transparencyInteractionYesDoes your business use AI that talks to your customers or the public? For example, a chatbot on your website, an AI assistant in your app, or an automated system that answers customer questions by phone or message.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuine value beyond that by enumerating the return payload (highest tier, per-tier applicability, deadlines, maximum penalties, provider/deployer lean, driving answers) and by imposing the disclaimer-relay obligation. However, without an output schema, the return description is still a summary rather than a structural account.

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?

Three tight paragraphs: what it returns, how to collect inputs, and the legal caveat. The return list is long but every item is decision-relevant, and the input-collection warning is front-loaded before the disclaimer boilerplate.

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 an 11-parameter, 10-required classification tool with no output schema, the description covers what an agent needs: the return contents, the ask-don't-guess protocol, the high-stakes fields, and the disclaimer obligation. The schema carries full parameter documentation, so nothing material is missing.

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 above that by explaining the design contract — each parameter's description is the question as asked of a person and its enum is the permitted values — plus flagging that the Annex III and prohibited-practices answers are the tier-critical ones. It does not add field-level syntax beyond that meta-guidance.

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: 'Classify how an organization builds or uses AI against the risk tiers of the EU AI Act', naming the exact regulation. An agent immediately knows this is a regulatory-tier assessment tool, which is clearly distinct from the listed siblings (ask_fidget_labs, list_offers, read_page).

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?

Gives concrete invocation guidance: 'Ask the person the questions rather than guessing', and warns that wrong answers on the Annex III domains or prohibited practices change the tier. It also mandates relaying the disclaimer. What's missing is any exclusion or scoping guidance (e.g. when a jurisdiction question falls outside the EU AI Act), but there is no competing sibling to route against.

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.