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

Annotations only cover the safety profile (readOnly, idempotent, non-destructive), but the description goes well beyond them: it defines accuracy as supported/(supported+contradicted), warns that accuracy_state values like not_enabled/no_facts/no_claims/pending mean 'no value, never zero', clarifies that inconclusive and not_covered are not errors in the answer, and explains that sources cite alongside a contradiction rather than causing it. That is substantial interpretive context not available from structured fields.

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 purpose and the sibling contrast, then the summary/claims contents, then a compact block of interpretation caveats. Sentences are dense and each carries semantics, though the paragraph is long enough that some caveats could be ordered more tightly.

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?

There is no output schema, so the description carries the return-value burden and does so: it details what the summary view returns (accuracy, coverage by topic and engine, contradicted claims with the contradicting fact, sources) and what the claims view returns (quote, verdict, facts used) plus pagination. Nothing an agent needs to call or interpret the result is missing.

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 and the schema already documents view, limit, topic, cohort, cursor, engine, verdict, audit_id and market_id. The description still adds real meaning on top: it explains the summary vs claims distinction, states the default page size (50) and that next_cursor should be passed back, and ties verdict/cohort behavior to the claims view.

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+scope: reads fact-checking verdicts of AI answers against the brand's confirmed facts, broken into summary and claims views. It explicitly distinguishes itself from the neighbouring read_perception tool by dimension (accuracy vs tone), so an agent can pick correctly without opening schemas.

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?

Names the alternative and the condition that selects it ('Use read_perception for tone rather than accuracy'), and adds operational guidance on how to report ('always state the coverage and quote the fact') plus which verdict value to pick to find errors. Nothing about tool selection is left to inference.

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