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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true. The description adds substantial behavioral context beyond these: the dual-pipeline routing logic, the precise meaning of could_not_verify (including verification_error{stage,detail} and the instruction that it is NOT evidence and must not be shown as one), and the distinction between unsupported vs. could_not_verify. This is exactly the kind of operational nuance an agent needs to interpret results correctly, and it complements rather than contradicts the annotations.

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 longer than typical but earns its length: it packs trigger phrases, use instructions, pipeline routing, verdict definitions, error semantics, and efficiency benefits into a coherent flow. It is front-loaded with the most critical info (what it is) and organizes details logically. Could be slightly condensed, but every sentence adds value given the tool's complexity.

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?

Despite lacking an output schema, the description provides a complete picture: all six verdict values, the inclusion of grounded/structured actual value with citation, reasoning output, and the critical error-handling semantics. It also covers the two distinct operational paths and explains when each is used. Given the tool's moderate complexity, this is thorough and self-sufficient for an agent to select and 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 description coverage is 100%, so the baseline is 3. The description goes further by explaining the tolerance_pct semantics ('Overrides the tolerance implied by the claim wording — set 1–2 for hallucination detection') and giving concrete examples for the claim parameter. This adds decision-relevant meaning beyond the schema's basic field descriptions.

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 explicit trigger phrases ('Is it true that…', 'fact check', 'verify the claim that…') and states the core function: natural-language claim verification against authoritative sources. It clearly differentiates from siblings by naming the two verification paths (structured SEC EDGAR for company-financial claims, grounded pipeline for all others) and describing the verdict output.

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,' which is clear when-to-use guidance. It doesn't explicitly state when not to use or name a specific alternative, but it provides strong contextual cues by distinguishing claim types and noting it replaces 4–6 sequential calls, implying efficiency. A slight miss is lack of exclusionary guidance (e.g., for open-ended research instead of verification).

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