Classify AI risk (EU AI Act)

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

Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context: 'Offline' (no network calls), 'checked against Regulation (EU) 2024/1689' (authoritative source), 'not legal advice' (limitation disclaimer), and it describes the output as 'risk tier + cited rationale'. This goes beyond the annotations without contradicting them.

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?

The description is a single, front-loaded sentence starting with the verb and resource, followed by two terse context clauses. Every element earns its place with no redundancy or filler.

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 4-parameter tool with no output schema, the description covers the return contract (risk tier + rationale), the legal basis, offline behavior, and disclaimer. Combined with the comprehensive schema descriptions, it is largely complete; the only gap is explicit sibling differentiation, which is covered under usage guidelines.

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 100%, with each parameter having thorough meaning including enum semantics and special guidance (e.g., domain breadth, audience selection, use_case phrasing). The tool description itself adds no further parameter information, but the schema carries the full burden, so the baseline 3 applies.

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?

The description uses the specific verb 'classify' with a clear resource ('an AI use case under the EU AI Act') and outcome ('risk tier + cited rationale'). It is immediately clear what the tool does and is distinct from sibling tools like explain_obligation or generate_disclosure.

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?

The description implies usage whenever classification under the EU AI Act is needed, but does not explicitly state when to use this tool instead of siblings like explain_obligation or check_record. The 'Offline' and 'checked against Regulation' context hints at behavior, but there are no exclusions or alternative references, so guidance is implied rather than explicit.

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