Classify EU AI Act Risk Tier

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

Annotations already declare readOnly/idempotent/non-destructive and closed-world, so the safety profile is covered. The description adds meaningful behavior beyond that: it discloses the evaluation basis (Annex III/VI, deployment context, capabilities, affected populations) and the return payload (tier, applicable articles, conformity assessment actions, compliance roadmap).

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

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

Front-loaded with the core action and outputs, then usage guidance and an explicit exclusion. Every sentence carries distinct information (purpose, criteria, returns, routing), with no redundant restatement of the tool name.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a classification tool with no output schema, the description usefully summarizes what is returned (tier, articles, conformity actions, roadmap) and the evaluation criteria. It is nearly complete, with the only gap being coverage of the several undocumented input parameters.

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

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

Schema description coverage is only 11% (one documented property of nine), so the description must compensate. It hints at deployment_sector, is_fully_automated, and the biometric/emotion flags, but omits others such as trust_score_overall, social_scoring_purpose, and affects_natural_persons, leaving significant parameter meaning unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb (classify) and resource (AI system into an EU AI Act risk tier), enumerates the four possible outcomes, and specifies the input basis (deployment sector, automation level, biometric/emotion-recognition use). It also names the criteria used (Annex III and Annex VI), so an agent knows exactly what this tool produces.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicitly routes: 'Use this for what EU AI Act category does this system fall into questions' and 'Do NOT use this for a general maturity/gap assessment... use `rai_compliance` with framework=EU_AI_ACT instead.' This gives both the trigger condition and the named alternative for the excluded case.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.