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

Annotations already declare read-only, idempotent, and open-world. The description adds critical behavioral nuance: the two routing paths (SEC EDGAR for company-financial claims, grounded pipeline for anything else) and the essential caveat that could_not_verify means the check did not happen and must not be interpreted as evidence. It also details the return payload including verdict, actual value, citation, and reasoning, going well beyond annotation hints.

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 long but structured: triggers, core function, path routing, return values, and an explicit warning. Every sentence adds information—no filler. However, the sentence about SEC EDGAR and XBRL math is dense and could be simplified without losing meaning, and the caveat about could_not_verify is embedded in the flow rather than highlighted.

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?

With no output schema, the description fully covers return types and edge semantics. It explains when to use the tool, what it returns, how it handles company-financial vs. other claims, and the distinction between unsupported and could_not_verify. The 4–6 calls replacement gives a clear value proposition. This is comprehensive for the tool's complexity.

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 input schema already documents both parameters with 100% coverage. The description enriches this by explaining tolerance_pct's role in overriding the claim's implied tolerance and gives a specific use case (set 1–2 for hallucination detection) and the default cap at 5. It also provides concrete claim examples for the `claim` parameter.

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 five natural-language trigger phrases and then states the core function: 'natural-language claim verification against authoritative sources.' It specifies a clear verb-resource pairing and distinguishes itself by outputting verdicts (confirmed/refuted/etc.), which differentiates it from broader research tools like deep_research or ask_pipeworx_grounded.

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?

Explicitly instructs 'Use whenever the agent needs to check whether something a user said is factually correct,' which anchors the tool's context. It also explains that it replaces 4–6 sequential calls, giving a strong signal for when to prefer it over a multi-step retrieval approach. However, it does not name any sibling alternatives or state exclusions, such as when a broader research tool would be better.

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