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

Beyond the annotations (readOnlyHint, openWorldHint, idempotentHint, destructiveHint false), the description exposes important behavioral nuances: the SEC EDGAR fast path vs. grounded fallback, the meaning of each verdict type, and crucially, the distinction between 'could_not_verify' (verification failed, must not be treated as evidence) and 'unsupported' (no source found). This significantly enhances the agent's ability to 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 richly informative but efficiently organized. It opens with concrete invocation phrases, then states purpose, describes processing paths, lists output types, and ends with critical caller caveats. Every sentence carries unique information; no filler or repetition. It is long but necessary for such a multi-path, high-stakes verification tool.

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?

Despite no output schema, the description fully documents the return values (verdicts, actual value with citation, reasoning) and explains error semantics. It covers the two distinct execution paths, routing logic, and the important negative case ('could_not_verify'). The description is complete for a tool of this complexity, leaving no major operational 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?

While schema coverage is 100%, the description adds substantial value beyond field descriptions. For 'claim' it provides realistic examples ("Apple's FY2024 revenue was $400 billion"), and for 'tolerance_pct' it explains how it overrides implied tolerance, recommends values for hallucination detection (1–2), and clarifies the default behavior (implied by wording, capped at 5). This goes well beyond the schema's basic descriptions.

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 function: natural-language claim verification against authoritative sources. It uses strong action phrases ('fact check', 'verify the claim that') and provides concrete examples. It also distinguishes itself from sibling tools by focusing on factual claim verification rather than general search or research, and explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct.'

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 provides explicit when-to-use guidance ('Use whenever the agent needs to check whether something a user said is factually correct') and explains the two-path routing for company-financial vs. other claims. It also notes efficiency ('Replaces 4–6 sequential calls'). However, it does not explicitly name alternative tools or state when not to use this tool, so it lacks the full when-not/alternatives coverage that would merit a 5.

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