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

The description goes far beyond the annotations (readOnly, openWorld, idempotent, non-destructive) by detailing internal behavior: structured SEC EDGAR + XBRL path for company-financial claims, grounded pipeline for others, exact percent-delta math, and the meaning of each verdict. Critically, it clarifies the distinction between 'could_not_verify' (check did not happen, not evidence) and 'unsupported' (no source), which is essential for correct interpretation. No contradictions with 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?

Although the description is long, every sentence adds value. It is front-loaded with example queries and a clear purpose, followed by routing details, return values, and caveats. The structure is logical and the length is justified given the tool's complexity (two pipelines, multiple verdicts, error semantics). No filler or redundancy.

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?

The description is comprehensive for a complex claim-verification tool with no output schema. It covers input semantics, processing steps, return values (verdict types with meaning), citation format, and error handling. It also provides usage guidance for two distinct claim categories, making it complete for the agent to invoke and interpret results 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 coverage is 100% with each parameter having a description. The tool description enhances this by providing concrete example claims, explaining that tolerance_pct overrides the implied tolerance, and giving a specific use case (1–2 for hallucination detection). This adds meaning beyond the schema's basic 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 states the tool performs natural-language claim verification against authoritative sources, with examples like 'fact check' and 'verify the claim that…'. It clearly distinguishes itself from generic query tools by focusing on fact-checking and even outlines two distinct verification paths (SEC EDGAR fast path vs. grounded pipeline), setting it apart from sibling tools.

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 also differentiates use cases for company-financial claims vs. other factual claims, explaining the routing logic. While it doesn't mention exclusions, it gives clear context and even notes it replaces multiple sequential calls, which helps the agent select this tool over alternatives.

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