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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive hints, and the description adds substantial behavioral nuance beyond that. It explains the meaning of each verdict, the critical distinction between 'could_not_verify' (check did not happen, not evidence) and 'unsupported' (no source exists), and the error structure (verification_error with stage/detail). It also discloses the fallback behavior and the fact that it replaces multiple sequential calls, which is not inferable from 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 comprehensive yet efficiently structured, opening with trigger phrases that aid tool selection, then outlining the two execution paths, return values, and key caveats. Every sentence contributes unique information—no fluff or restatement of the title. While lengthy (about 150 words), the complexity of the tool justifies the detail and it remains well-organized.

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 absence of an output schema, the description fully compensates by explaining the return format (verdict, actual value with citation, reasoning), edge cases (could_not_verify vs unsupported), and internal mechanics (SEC EDGAR fast path, grounded fallback). It also provides usage context and error handling, making the tool's behavior clear for an agent even without structured output information. This is complete for the tool's complexity.

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?

The input schema already provides full descriptions for both parameters (claim with examples, tolerance_pct with range and default). The description adds minimal extra parameter semantics: it mentions 'exact percent-delta math' and the ability of tolerance_pct to override implied wording, but these are largely redundant with the schema. Since schema coverage is 100%, a baseline score of 3 is appropriate.

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 the tool verifies natural-language factual claims, with explicit example triggers ('fact check', 'verify the claim that...') and distinguishes itself from general Q&A tools by returning a verdict. It specifies a concrete resource (authoritative sources, SEC EDGAR for financials) and a unique composite behavior (replacing 4–6 sequential calls), which separates it from sibling tools like ask_pipeworx.

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 says 'Use whenever the agent needs to check whether something a user said is factually correct,' providing a clear when-to-use directive. It also details two distinct execution paths (SEC EDGAR for company-financial claims, grounded pipeline for others), giving context on how it handles different claim types. However, it does not name alternative tools or state explicit 'when not to use' scenarios, so it misses the top bar.

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