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

Annotations already declare readOnlyHint=true, openWorldHint=true, idempotentHint=true, destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral nuance beyond annotations: it states the exact verdict taxonomy, warns that could_not_verify means the check did not happen and must not be presented as evidence, and explains the unsupported meaning. It also mentions the return of pipeworx:// citations and reasoning. Minor gap: it does not describe latency/rate-limit behavior, but for a read-only tool this is adequate.

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 information-dense, front-loaded with trigger phrases and a clear purpose statement. Every section adds value: routing, verdicts, error semantics, and the efficiency claim. It could be slightly tightened (e.g., the parenthetical list of examples is a bit long), but it earns its length by covering critical caller guidance that isn't available elsewhere.

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 2 params, high schema coverage, read-only annotations, and no output schema, the description does a strong job of covering what the agent needs to invoke this tool correctly: when to use it, what kinds of claims go where, the meaning of each verdict, and the critical could_not_verify warning. The absence of an output schema raises the burden to explain return values, which the description does (verdict, actual value, citation, reasoning). Minor deduction: it doesn't detail the exact percent-delta math or citation format, but that's likely unnecessary for correct invocation.

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 adds meaning by explaining the overall claim->verdict flow and by clarifying tolerance_pct as an override "implied by wording" with a default "capped at 5" and guidance for hallucination detection (set 1–2). That goes beyond the schema's terse description. A 4 is appropriate because the schema already documents parameters well and the description enriches them rather than repeating.

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 triggers ("Is it true that…", "fact check") and a clear verb+resource: natural-language claim verification against authoritative sources. It distinguishes itself from siblings by naming the structured SEC EDGAR + XBRL fast path for Company-financial claims and a grounded pipeline for any other factual claim. The verdict list and replacement of 4–6 sequential calls further clarify its unique role.

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 it: "Use whenever the agent needs to check whether something a user said is factually correct." It also gives direct routing guidance (Company-financial claims use the SEC EDGAR fast path; ANY OTHER factual claim falls through to the grounded pipeline) and explains what each outcome means (could_not_verify vs unsupported). This is strong when-to-use guidance.

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