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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds the shape of results (claim attribution plus per-publisher reviews) but omits pagination behavior, rate limits, or coverage caveats that would help interpret sparse results.

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?

Three front-loaded sentences with no filler; the source list and the result-field enumeration both do real work. The field enumeration is slightly redundant against the existing output schema, keeping it from a 5.

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 an output schema present, return values need not be explained, and the description covers corpus scope and a usage trigger. It leaves the filtering parameters (language, recency, publisher) entirely to the schema, which is acceptable but leaves the tool's narrowing behavior under-explained.

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 80%, so the schema already documents claim, limit, language, max_age_days and publisher_site. The description adds no syntax or filtering guidance beyond what the schema provides, so the baseline 3 applies.

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 (search) and resource (published fact-checks) and names the source organizations, which immediately differentiates it from siblings like check_grounding or inspect_source. An agent knows exactly what corpus this queries.

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?

"Start here when checking a claim that has circulated publicly" gives a clear entry-point condition. However, it never names alternatives or states when NOT to use it (e.g. for private or unverified claims, where check_grounding might be better).

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