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

Goes far beyond the readOnly/openWorld/idempotent annotations by disclosing critical behavioral nuances: could_not_verify means the check did not happen and must not be shown as evidence, unsupported means no source was found, and errors carry verification_error{stage,detail}. It also details the two verification paths and tolerance override behavior—exactly the kind of context an agent needs.

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?

Long but well-structured: starts with natural-language triggers and a one-liner purpose, then provides routing details, return values, and an important caller warning. Every sentence carries operational weight, though some trimming could make it tighter. The front-loaded purpose earns a strong score.

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 no output schema, the description fully explains the return verdict enum, the cited actual value, reasoning, and error semantics. It also describes the two execution paths, tolerance behavior, and the composite nature of the tool. Nothing essential is missing for an agent to invoke it 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 already covers both parameters with 100% descriptions, so baseline is 3. Description adds value by explaining tolerance_pct's default ('implied by wording, capped at 5') and use cases ('set 1–2 for hallucination detection'). It also gives concrete examples for the claim parameter, enriching the schema semantics.

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?

Description opens with explicit natural-language triggers ('fact check', 'verify the claim that…') and clearly states the resource: natural-language claim verification against authoritative sources. It distinguishes from sibling tools by focusing on factual claims and noting it replaces 4–6 sequential calls, making its composite purpose unmistakable.

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?

Provides explicit usage guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains the routing logic between company-financial claims (SEC EDGAR fast path) and other claims (grounded pipeline), giving clear context. It stops short of naming direct alternative tools, but the scope is sufficiently demarcated.

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