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

Beyond the annotations (readOnlyHint, idempotentHint, etc.), the description discloses crucial behavior: what could_not_verify means (the check did not happen, carries verification_error{stage,detail}, and must not be shown as evidence), what unsupported means (no source coverage), and the return structure (verdict, evidence with citation, reasoning). This is precisely the kind of context that helps agents interpret results correctly.

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 dense but every sentence earns its place: trigger phrases, usage guidance, pipeline distinction, return values, error semantics, and efficiency note. It is front-loaded with how to recognize calls and structured logically. No wasted words, despite the length.

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?

No output schema means the description must explain return values, and it does: verdict enums, actual value with citation, and reasoning. It also covers error conditions, the two routing paths, and performance benefits. For a tool of this complexity, the description is fully complete and leaves no critical gaps for an agent.

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%, but the description adds significant value by explaining tolerance_pct semantics: it overrides the implied tolerance, defaults to wording-capped-at-5, and suggests 1–2 for hallucination detection. It also provides concrete claim examples for the claim parameter, going beyond the schema's basic description.

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 states exactly what the tool does: 'natural-language claim verification against authoritative sources.' It includes trigger phrases like 'fact check' and 'verify the claim that...' and details two distinct processing paths (SEC EDGAR for company-financial claims, grounded pipeline for others), which clearly distinguishes it 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?

The description explicitly says to use it 'whenever the agent needs to check whether something a user said is factually correct' and even notes it 'replaces 4–6 sequential calls,' implying it is a consolidated alternative. However, it does not explicitly name alternative sibling tools or state when not to use it (e.g., for open-ended research), so it falls 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.