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

Annotations declare readOnly/openWorld/idempotent, but the description adds critical semantics beyond that: the distinction between could_not_verify (check failed, not evidence) and unsupported (no source covered), the default tolerance cap of 5%, and the exact verdict list. These details prevent misinterpretation of results, exceeding annotation coverage.

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 lengthy, the description is front-loaded with query examples and every sentence serves a purpose: routing logic, return format, error semantics, and efficiency gains. It avoids fluff and maintains a clear logical flow from invocation to output interpretation.

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 takes on the burden of explaining return values, and it does so thoroughly: verdict types, grounded/structured value with citation, reasoning, and even verification_error structure details. It also explains the fallback pipeline and covers edge cases, making it complete for a tool with this 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?

Schema already covers 100% of parameters with descriptions, so baseline is 3. The description adds extra value by explaining tolerance_pct's override behavior and giving a concrete use case (set 1–2 for hallucination detection), which the schema does not convey. Claim examples also illustrate expected input formats, slightly enriching the schema.

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 uses a specific verb+resource: 'natural-language claim verification against authoritative sources,' with concrete example phrasings ('is it true', 'fact check'). It clearly distinguishes the tool's niche from siblings by positioning it as a fused multi-step claim checker, and mentions replacing 4–6 sequential calls, making its 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?

Explicitly states when to use: 'Use whenever the agent needs to check whether something a user said is factually correct.' It further provides routing guidance for company-financial claims vs all other factual claims, and gives actionable tolerance_pct advice for hallucination detection. No alternatives are named, but the context is unambiguous.

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