Skip to main content
Glama

ai_act_risk_tier_classifier

Read-onlyIdempotent

[Deterministic EU AI Act Risk Tier classification. Pure statutory logic, read-only, side-effect free]. Evaluates an AI system under Regulation (EU) 2024/1689 (EU AI Act), auditing Prohibited Practices (Art. 5), High-Risk classifications (Annex III and safety components Annex I), Specific Transparency obligations (Art. 50), and General Purpose AI model tiers (GPAI 10^25 FLOPs). Usage: Use this tool to establish official legal risk tier, statutory deadlines (2025/2026/2027), and mandatory compliance steps for AI systems. Returns: JSON object with { legalRiskTier: string, prohibitedPracticeTriggered: boolean, highRiskCategory: string | null, transparencyObligations: array, gpaiStatus: object, statutoryDeadlines: array, complianceChecklist: array, legalCitation: string }.

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": {
      "systemName": "<systemName>",
      "useCaseDomain": "<useCaseDomain>"
    },
    "name": "ai_act_risk_tier_classifier"
  }
}

Input Schema

NameRequiredDescriptionDefault
systemNameYesIdentifier or commercial name of the AI system
useCaseDomainYesOperational functional domain under EU AI Act Regulation (EU) 2024/1689
gpaiTrainingComputeFlopsNoCumulative training compute FLOPs (threshold: 10^25 FLOPs for systemic risk)
hasHumanInTheLoopOversightNoWhether meaningful human oversight is configured (Art. 14)
isDirectInteractionWithHumansNoWhether the system interacts directly with natural persons (Art. 50(1))
generatesSyntheticMediaOrDeepfakesNoWhether the system generates deepfakes or synthetic media (Art. 50(2))
isSafetyComponentOfRegulatedProductNoWhether AI is a safety component of products in Annex I (medical devices, machinery, civil aviation)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare readOnlyHint and idempotentHint, and the description reinforces these consistently by calling the tool deterministic, 'pure statutory logic', and side-effect free, which tells the agent repeat calls are safe and results are reproducible. It also discloses the return payload, valuable because no output schema exists. It stops short of stating limitations such as jurisdiction assumptions or whether input data is logged.

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 compact blocks — bracketed nature-of-tool header, explicit Usage line, explicit Returns line — all front-loaded with zero filler. Even the return-field enumeration earns its place because there is no output schema.

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 7-parameter classification tool with no output schema, the definition supplies exactly what is missing: the legal framing, the when-to-use condition, and the full shape of the JSON result. An agent has enough to decide to call it and to interpret the response without further context.

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 coverage is 100%, so the schema already documents every parameter, including the 10^25 FLOPs threshold and the Art. 14/50(1)/50(2) semantics of the booleans. The description adds only a light mapping from the audited articles to those inputs and does not, for example, explain how useCaseDomain drives the high-risk Annex III category. Baseline 3 is appropriate.

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 uses a specific verb and resource ('Risk Tier classification' under Regulation (EU) 2024/1689) and enumerates the exact statutory layers it audits: Art. 5 prohibited practices, Annex I/III high-risk, Art. 50 transparency, and GPAI 10^25 FLOPs. That is far more precise than a generic compliance checker, but it never explicitly contrasts itself with related siblings such as eu_ai_act_check or ai_act_technical_dossier_builder, so the boundary is inferred rather than stated.

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?

The 'Usage:' line gives a clear triggering condition — establish the official legal tier, statutory deadlines (2025/2026/2027), and mandatory compliance steps. However, it offers no exclusions or alternatives, so an agent cannot tell from the definition alone whether to call this versus the dossier builder or the general EU AI Act check.

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