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

Beyond the readOnly/idempotent annotations, the description discloses the two-route verification logic, the complete set of possible verdicts, and — critically — the semantic distinction between 'could_not_verify' (check failed) and 'unsupported' (no source found), warning that 'could_not_verify' must not be used as evidence. This is valuable behavioral detail that annotations do not capture.

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 the description is long, it is tightly structured with no fluff: trigger phrases at the start, then the use case, pipeline split, output shape, and two important caveats. Every sentence adds unique information, and the progression is logical and front-loaded.

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 and the absence of an output schema, the description fully specifies all six verdicts, the included evidence and citation, and the error-handling semantics. Combined with complete parameter schema coverage and clear annotations, this leaves no significant gaps for correct tool invocation and use.

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 describes both parameters (claim and tolerance_pct) with detailed explanations and defaults, so the description adds little parameter-level meaning. It mentions 'exact percent-delta math' and the tolerance override, but this is more about tool behavior than new parameter semantics, so the baseline 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 clearly identifies this as a natural-language claim verification tool, with explicit trigger phrases and a stated purpose: checking whether a user's claim is factually correct. It distinguishes itself from sibling Q&A tools by detailing the verdict-based output and the two internal pipelines (SEC EDGAR for financial claims, grounded pipeline for everything else), which is a unique capability.

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 gives clear usage context: "Use whenever the agent needs to check whether something a user said is factually correct" and lists typical trigger phrasings. It does not explicitly name alternative tools to avoid or state when not to use this tool, though the phrase 'Replaces 4–6 sequential calls' implies it is the consolidated claim-checking choice.

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