Audit text

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds real value beyond that: it is deterministic with no language model, returns findings carrying severity, span, expected/found values and sources, and explicitly disclaims certification of compliance. It does not mention rate limits or text-size limits, but it is a batch read with nothing destructive to disclose.

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 core operation and scope are front-loaded in the first clause, followed by the output shape and the legal caveat. The prose is dense and every clause carries information, though the long parenthetical enumerations make single sentences heavier than necessary.

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?

With no output schema, the description carries the return-value burden and does so: it names the finding fields (severity, span, expected, found, sources). Combined with the deterministic/no-LLM note, the disclaimer, and the parameter semantics already in the schema, an agent has everything needed to call and interpret it.

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%, so the baseline is 3. The description still adds meaning by explaining that as_of selects the version of the Act in force and that the text may be any length, framing what the checker actually inspects. It adds marginal rather than decisive detail over the schema, so it sits just above baseline.

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 (checks a text against the AI Act) and enumerates the three concrete check classes: outdated application dates, citations to removed/nonexistent provisions, and altered quotations. It is clear enough to separate from siblings by scope (whole document vs. a single citation), but it never names a sibling such as aiact_verify_citation to make the boundary explicit.

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 by listing accepted inputs (policy, provider answer, slides, AI-generated answer) and adds a clear caveat that results are orientation only and never certify compliance. However, it gives no explicit when-to-use or when-to-prefer-an-alternative guidance relative to aiact_verify_citation or aiact_obligations, leaving routing to inference.

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