Ask open EU AI Act questions

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

Goes well beyond the annotations by disclosing the write requirement ('Requires assessments:write'), the persistence model ('Answers are kept on the project for later scans'), and the side effect of re-checking the tier after each answer. It never addresses the destructiveHint=true flag, so the agent gets no signal about whether existing answers can be overwritten.

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?

Dense but front-loaded: the action, dialog behavior, and termination rule come first, then parameter rules, then the permission note. A few clauses (the quoting around 'Not sure', the suggestFromCode caveat) are compressed to the point of being hard to parse on first read.

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?

No output schema exists, yet the round-trip contract (returning notSureFactPaths for reuse) is implied rather than stated, leaving some ambiguity about what a single call actually returns. Everything else an agent needs to invoke it correctly — loop semantics, skip list, suggestion limits, auth scope — is present.

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?

With only 33% schema description coverage, the description carries real weight: it defines skipFactPaths as the previous call's notSureFactPaths and restricts proposedAnswers to facts marked suggestFromCode, explicitly forbidding suggestions about system use or affected persons. assessmentPid remains unexplained in both schema and description.

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: ask the person the open EU AI Act questions, one at a time, with a defined dialog shape and termination condition. It does not name or contrast the closest sibling (air_ask_screening_questions or air_list_open_facts), so the agent must infer which 'ask' tool applies.

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?

Clear operational context: drive the loop until no question is open or all remaining ones are 'Not sure', and feed notSureFactPaths back as skipFactPaths. It also constrains proposedAnswers to suggestFromCode facts. It stops short of naming alternatives to use when the agent should not be asking questions interactively.

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