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

The description goes well beyond the annotations (readOnly, openWorld, idempotent). It discloses the two verification routes, the specific verdict types returned, the meaning of 'could_not_verify' (verification_error, not evidence) and 'unsupported' (no source found), and even warns callers not to display could_not_verify as evidence. It also explains the default and override behavior of tolerance_pct. This is rich, non-obvious behavior.

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?

While the description is detailed, every sentence delivers essential information. It opens with recognizable query patterns, explains the tool's scope, breaks down two code paths, describes return values and edge cases, and ends with a clear 'Replaces 4–6 sequential calls' statement. The structure is logical and efficient with no filler.

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?

The description is complete for a tool with no output schema. It explains the return format (verdict, actual value with citation, reasoning) and explicitly defines the two failure verdicts ('could_not_verify' and 'unsupported'), including how to treat them. With annotations already covering safety and idempotency, and parameters fully documented in schema, the description fills all gaps.

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 baseline is 3. The description adds meaningful context beyond the schema: it gives natural-language examples for the claim parameter and explains how tolerance_pct overrides the implied tolerance (e.g., set 1–2 for hallucination detection) and that the default is capped at 5. This helps callers know how to set the parameter in different scenarios.

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 clearly states the tool's purpose: natural-language claim verification against authoritative sources, with explicit query examples ('Is it true that…', 'fact check' etc.). It specifies the resource (claims) and the verb (validate/verify), and it stands apart from siblings by emphasizing its end-to-end claim-checking capability that replaces multiple sequential calls.

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 says 'Use whenever the agent needs to check whether something a user said is factually correct,' which is a clear use case. It also explains the two distinct paths (company financial claims via SEC EDGAR vs. other claims via grounded pipeline), but it does not explicitly name alternative tools to use instead or provide exclusion criteria. This is clear context without explicit alternatives.

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