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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses critical behavioral nuances: the fallback routing logic, the specific verdict types, the meaning of 'could_not_verify' (which is not evidence for/against and must not be presented as such), and the distinction between 'unsupported' and 'could_not_verify'. This provides the agent with essential context for interpreting results safely and accurately, going far beyond what annotations alone offer.

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 every sentence earns its place. It is front-loaded with examples, then covers usage, pipeline, output, and an important caller warning. The structure is logical and the content is dense without fluff. Given the tool's complexity, the length is justified and nothing feels redundant.

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 must carry the burden of explaining return values, and it does—listing the verdict types and the verification_error field. It also covers edge cases (e.g., 'could_not_verify' vs 'unsupported'), routing behavior, and high-level performance (replaces 4-6 calls). For a 2-parameter tool with no nested objects, this is exceptionally complete and leaves no critical 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?

The schema descriptions for both 'claim' and 'tolerance_pct' are already detailed, but the tool description adds even more meaning. It explains that 'claim' is a natural-language factual claim and gives examples; it elaborates on 'tolerance_pct' by explaining how it overrides implied tolerance, giving a use case for hallucination detection, and stating the default. This enriches the parameter semantics beyond the schema, fully compensating for any ambiguity.

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 purpose: natural-language claim verification/fact-checking against authoritative sources. It uses specific verbs like 'verify', 'confirm or refute', and provides example phrases that trigger its use. It also distinguishes itself from siblings by describing its dual pipeline (SEC EDGAR for company-financial claims, grounded pipeline for everything else) and by noting it replaces 4-6 sequential calls, making its role unique.

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 states when to use the tool: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also provides concrete example phrasing and clarifies the routing behavior for different claim types. It does not explicitly list exclusions, but the guidance is concrete and clearly positions this tool as the primary fact-checking resource among siblings.

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