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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses important runtime behavior: it routes claims differently based on domain, returns a structured verdict set, and attaches pipeworx:// citations. It also defines tricky result states—could_not_verify means the check didn't happen and must not be treated as evidence, while unsupported means no source exists. This is rich behavioral context that annotations alone don't provide.

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?

Although longer than a simple two-sentence description, every sentence earns its place: it opens with query examples, states the use case, describes routing, defines the return payload, explains critical caller caveats, and even notes the tool replaces 4–6 sequential calls. It is front-loaded and information-dense without redundancy.

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?

Given the tool's complexity (two routing paths, multiple verdicts, error states) and the lack of an output schema, the description covers all necessary context: what it returns (verdict, actual value, citation, reasoning), how to interpret edge cases (could_not_verify vs unsupported), and the composite nature (replaces multiple calls). The agent has enough information to invoke and interpret results correctly.

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?

The schema already provides 100% coverage for both parameters, and the description adds extra meaning: claim is shown with real-world examples, and tolerance_pct is explained as overriding the claim's implied tolerance with a suggestion to use 1–2 for hallucination detection. This enriches the schema's minimal definitions.

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 opens with concrete natural-language triggers ('Is it true that…', 'fact check', 'verify the claim that…') and clearly states the tool validates claims against authoritative sources. It specifies the two routing paths (SEC EDGAR for company financials, grounded pipeline for everything else), which distinguishes it from sibling ask_pipeworx tools by focusing on fact-checking rather than general Q&A.

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 'Use whenever the agent needs to check whether something a user said is factually correct,' providing a clear invocation condition. It also explains when the SEC EDGAR fast path applies versus the grounded pipeline. However, it doesn't name specific alternative tools or state explicit 'when not to use' scenarios, so it doesn't fully earn a 5.

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