Classify AI System Under EU AI Act

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

Annotations already declare readOnlyHint=true and idempotentHint=true. Description adds behavioral details: signal precedence, return of follow-up questions, and that Art.6(3) cannot be auto-applied. No contradictions.

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?

Four sentences, no fluff. Purpose first, then inputs, then behavioral note, then outputs and reference. Every sentence adds value. Front-loaded with primary function.

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?

Given complexity of EU AI Act classification and many signals, description covers inputs, behavioral precedence, output contents, and links to related tool for Art.6(3). Output schema exists, so no need to detail return values. No gaps.

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 50%, but description adds context by grouping signals (domain, biometric flags, synthetic content) and explaining precedence. Does not repeat schema details but provides useful overview. Adds beyond schema.

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?

Description clearly states the tool classifies AI system risk under EU AI Act, distinguishes from sibling tools by referencing the separate tool for Art. 6(3) exceptions. Verb 'classify' with specific resource 'AI system's risk level' and scope is clear.

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?

Description explicitly explains when to use (classification) and when not (Art. 6(3) exceptions should use euaiact_assess_art6_3_exception). Also states that signals take precedence over text matching, guiding proper input strategy.

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