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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive, so the description's value comes from adding non-obvious behavioral details: the two pipeline routes with exact percent-delta math, and the critical distinction between could_not_verify (check did not happen, must not be shown as evidence) and unsupported (no source exists). It also exposes the structured verification_error{stage,detail}, 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?

At roughly 115 words, the description is dense but well-organized, front-loading trigger phrases and a clear purpose before detailing pipelines, return values, and error semantics. Every sentence contributes essential context for a tool with complex behavior, though a slightly tighter presentation would improve readability.

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?

Without an output schema, the description carries the full burden of explaining return values, and it does so thoroughly by listing the six verdicts and clarifying the two most ambiguous ones. It also covers parameter behavior, routing logic, and efficiency trade-offs, making it self-contained for an agent to select and invoke the tool 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?

Schema coverage is 100% for the two parameters, so the baseline is 3; the description adds meaningful nuance by explaining how tolerance_pct overrides the tolerance implied by claim wording, including the 0.5–50 range and a concrete use case ('set 1–2 for hallucination detection'). It also notes the default cap of 5, which the schema does not state.

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 examples ('Is it true that…', 'fact check', 'verify the claim that…') and immediately states the tool performs 'natural-language claim verification against authoritative sources'. It names the specific verb+resource ('Validate Claim') and clearly differentiates from sibling research tools (e.g., deep_research, entity_profile) by focusing on verdict-based fact-checking.

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?

It explicitly says 'Use whenever the agent needs to check whether something a user said is factually correct' and then distinguishes between two routing paths (SEC EDGAR for company-financial claims, grounded pipeline for any other factual claim). It also notes it 'Replaces 4–6 sequential calls', implying it is a consolidated alternative, though it does not list formal exclusions beyond that implicit coverage.

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