classify_ai_system

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

Annotations already indicate readOnlyHint, idempotentHint, openWorldHint. Description adds behavioral context: it returns risk tier, category, Articles grounded verbatim in law, and uses EU AI Act regulation number. No contradictions, but no additional detail on auth or side effects beyond what annotations imply.

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?

Two sentences plus usage guidance. Front-loaded with core purpose, efficiently covers usage, returns, and alternatives. Every sentence adds value.

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 no output schema, description adequately explains return values (risk tier, category, Articles). It doesn't specify exact format but is sufficient for agent to understand output. All parameters are documented.

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 coverage is 100%. Description adds value: for 'description' it explains specificity improves precision and gives examples; for 'language' it lists language codes and explains they are EU official languages; for 'full' it clarifies inclusion of verbatim text.

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 it classifies AI systems under the EU AI Act, returning risk tier, Annex III category, and binding Articles. It distinguishes from sibling tools (lookup_article, search_eu_ai_act) by specifying its unique purpose.

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 says 'USE THIS when the user asks whether an AI system is high-risk or prohibited, what obligations apply, or which Articles bind a specific AI use-case.' It also names alternatives: 'For looking up one known Article use lookup_article; for keyword search use search_eu_ai_act.'

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