Verify citation

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the description's added value is the semantic limit disclosure: support_checked is always false and compliance is never certified. That is genuinely useful guardrail context a caller must not assume, though auth, rate limits, and the exact result shape remain undisclosed.

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?

Two dense sentences, front-loaded with the core action, and the negative guarantees are packed into a single clause with no filler. Every clause carries information.

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 is responsible for return context, and it partially delivers by naming the V0/V1/V2 check layers and one always-false response field (support_checked). It still leaves the overall response structure (found/applicable results, per-layer outcomes) to inference, which is the main remaining gap for a verification tool.

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 100%, so the baseline is 3, but the description maps the parameters to check tiers — as_of drives applicability (V1), lang drives the language check (V2), and the pinpoint (claimed_ref) participation in the V0 text match. That mapping is interpretive value the schema alone does not provide.

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 names a specific verb and resource ('Checks that a quotation exists in the AI Act text') and decomposes it into three precise sub-checks (verbatim presence with pinpoint, applicability at a reference date, language). This is clearly distinguishable from retrieval/search/diff siblings, which do not verify quotations.

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 states what the tool does NOT do ('never checks that the text supports a claim... never certifies compliance'), which is meaningful when-not guidance for a verification tool. It does not, however, point to a sibling for the adjacent task (finding a quote via aiact_search) or give a positive 'use this when' trigger.

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