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

Annotations already declare readOnly, idempotent, openWorld, non-destructive. The description adds significant behavioral context: the distinction between 'could_not_verify' (check did not happen) and 'unsupported' (no source exists), the exact percent-delta math for financial claims, and the return structure. It even warns callers not to treat could_not_verify as evidence. This goes far beyond 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 ideal, but every sentence carries weight: trigger phrases, dual-path explanation, verdict list, error semantics, and the efficiency gain. It front-loads the purpose and trigger phrases, and the critical 'IMPORTANT for callers' note is placed prominently. Slight redundancy in the phrase list could be trimmed, but it's well-structured.

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 the tool's complexity (two pipelines, six verdicts, error handling), the description covers everything an agent needs: when to use, what happens under the hood, what it returns, and how to interpret ambiguous outcomes. It even explains why it replaces multiple sequential calls. No gaps 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 coverage is 100% for both parameters. The description adds value by explaining tolerance_pct's role in hallucination detection (set 1–2 for strict checking) and noting the default is implied by wording capped at 5. It also provides a concrete example of the claim parameter. This goes beyond the schema's bare 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 clearly states it performs natural-language claim verification with specific trigger phrases ('fact check', 'verify the claim that...'), and explicitly defines its scope: company-financial claims via SEC EDGAR/XBRL fast path, all other claims via grounded pipeline. It distinguishes itself from siblings by naming the exact function and output verdict types.

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 says 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains the two routing paths (structured vs grounded) and mentions it replaces 4–6 sequential calls, making it clear this is the go-to tool for claim verification without ambiguity.

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