Ask the EU AI Act checklist before a scan

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

Goes beyond the annotations meaningfully: it clarifies that despite collecting answers it 'saves nothing itself,' which is critical for an agent to avoid assuming persistence, and it discloses the auth requirement ('Requires projects:read'). The 'saves nothing' note is consistent with readOnlyHint=true, adding real value.

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?

Front-loaded with the timing condition and dense with relevant facts—dialog behavior, answer filtering, return handling, save step, and permissions. Every sentence carries information, though it is a bit packed into one block.

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 read-only, single-param tool with no output schema, it covers what it does, when, how answers are returned, that it doesn't persist, and the next step. The only real gap is the unexplained projectPid.

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 0% and the description never explains projectPid or its format, so it does not compensate for the gap. The project context is only implied by 'the project already holds an answer for,' which is thin for a required param.

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+resource: it asks the person each EU AI Act screening question in its own dialog with defined answer options. It also names related siblings (air_start_assessment, air_save_prepared_answers), helping an agent place it in the flow. Not quite a 5 because the 'scan' relationship is assumed rather than fully defined.

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?

It gives a clear temporal condition ('Before a scan') and continues the workflow ('after air_start_assessment, send them with air_save_prepared_answers'), plus a useful exclusion rule (facts the project already answers are left out). No explicit when-not-to-use, but the surrounding context is clear.

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