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

The description significantly enriches the annotations by explaining failure modes: 'could_not_verify' means the check did not happen and carries verification_error, while 'unsupported' means no source exists. It also discloses the SEC EDGAR fast path for financial claims and the grounded pipeline for other claims, adding operational detail beyond the readOnly/idempotent hints.

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 dense and covers many aspects—usage triggers, routing, verdicts, caller warnings—but it remains well-organized and front-loaded. A few phrases like 'Replaces 4–6 sequential calls' could be trimmed, but overall every section earns its place and the structure aids comprehension.

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 fully specifies the return shape: verdicts, actual value with citation, reasoning, and the verification_error structure. It handles edge-case semantics (could_not_verify vs unsupported) and explains routing and tolerance behavior, making it complete for a complex verification tool.

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%, so the baseline is 3. The description adds extra semantic context by explaining how tolerance_pct interacts with the claim wording and how it can be used for hallucination detection ('set 1–2 for hallucination detection'), which goes beyond the schema's basic description of the parameter.

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 trigger phrases and explicitly states the tool performs natural-language claim verification against authoritative sources. It clearly distinguishes itself from sibling tools by focusing on verdict-based fact-checking rather than general Q&A or research, and gives a concrete example ('Apple's FY2024 revenue was $400 billion').

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 provides an explicit 'Use whenever' statement for fact-checking user claims and gives routing guidance for company-financial claims versus all other claims. It does not name specific sibling tools as alternatives or exclusions, but it clearly communicates when this tool is appropriate and how it falls back internally, which is strong guidance.

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