classify_eu_ai_act_system

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

Annotations already cover the safety profile (readOnlyHint, idempotentHint, openWorldHint=false), and the description adds genuinely new context: it depends on an optional `classify` extra and degrades to an install hint if absent. That dependency/failure-mode disclosure is exactly the kind of behavior annotations can't express.

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?

Three short lines with zero filler; the purpose leads, followed by invocation mechanics and the dependency caveat. Every sentence earns its place.

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?

An output schema exists, so return values need no explanation. The description covers purpose, input format, the schema-discovery trick, and the optional-dependency caveat — enough to call the tool correctly, with only the SystemProfile field structure left to a follow-up empty-string call.

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 0% and the single parameter has no description, so the description must compensate. It does explain the input is a JSON-encoded SystemProfile and that an empty string returns the schema, but it never says what fields the profile requires — the agent must make a discovery call to learn the shape.

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 and resource — 'Classify an AI system's EU AI Act risk tier' — plus a differentiator ('with pinpoint citations'). The sibling tools are all MiCAR-register related, so the EU AI Act framing alone cleanly separates this tool from every alternative.

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 explains how to invoke it ('Pass a SystemProfile as JSON; pass an empty string to get the schema') but never states when to use it versus the MiCAR siblings or what prerequisites must hold before calling. Usage is operational rather than selective, leaving selection to inference.

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