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

The description goes well beyond the readOnly/openWorld/idempotent annotations by explaining the two processing paths, enumerating all six verdict categories, and crucially distinguishing 'could_not_verify' (with verification_error, not evidence) from 'unsupported' (no source coverage). This is valuable behavioral context that prevents misinterpretation of results and is not available from annotations or schema.

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 description is somewhat long, but it is front-loaded with usage examples and each section (routing, verdicts, error semantics, replacement value) adds distinct, non-redundant information. It is well-organized and every sentence contributes, though a tighter structure could have been slightly more concise.

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?

Even though there is no output schema, the description fully specifies return values (verdict, actual value with citation, reasoning), explains all verdict outcomes, details error semantics (verification_error, unsupported vs could_not_verify), and outlines the two routing paths. This is a complete operational spec for an agent to invoke the tool correctly and interpret results.

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%: both 'claim' and 'tolerance_pct' are already well-documented with examples and semantics. The description does not add further parameter-level detail beyond what the schema provides, so the baseline of 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?

The description explicitly identifies the tool as a natural-language claim verification tool with concrete example phrasings ("Is it true that…", "fact check"), a clear verb-resource pair (verify claim), and differentiates it from generic lookup tools by stating it replaces 4–6 sequential calls. The purpose is unmistakable and distinct from sibling tools.

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?

Provides explicit guidance: "Use whenever the agent needs to check whether something a user said is factually correct" and outlines two routing paths (SEC EDGAR for financial claims, grounded pipeline for other factual claims). It notes the tool replaces a multi-step process, which implies a preference over sequential calls. However, it does not explicitly name alternative sibling tools or state when not to use them, so it falls slightly short of a 5.

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