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

The description goes well beyond the annotations by disclosing the exact verdict set, the special non-evidentiary meaning of `could_not_verify` (with `verification_error{stage,detail}`), the distinction between `could_not_verify` and `unsupported`, and the routing logic between SEC EDGAR and the grounded pipeline. It also mentions the output includes a pipeworx:// citation and reasoning, and clarifies the tolerance behavior.

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, covering trigger phrases, dual pipeline, verdicts, error semantics, and efficiency in a structured, logical order. It front-loads the purpose and examples before diving into nuances. Although it could be trimmed slightly (e.g., the efficiency claim at the end is somewhat tangential), the complexity of the tool justifies its length.

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 describes the return contract: the six possible verdicts, the actual value with citation, and reasoning. It also covers error semantics (`could_not_verify` vs `unsupported`), the two processing paths, and the optional tolerance parameter. For a two-parameter tool with rich annotations, this is a complete and self-contained description.

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 fully describes both parameters with examples and precise semantics (e.g., tolerance_pct range and default). The description reinforces the math ("exact percent-delta math") and the tolerance behavior, but it does not materially extend parameter-level guidance beyond the schema. With 100% schema coverage, a baseline 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 uses explicit trigger phrases ("Is it true that…", "fact check", "verify the claim that…") and clearly states the tool verifies natural-language claims against authoritative sources. It further distinguishes between company-financial claims (SEC EDGAR/XBRL fast path) and all other claims (grounded pipeline), and enumerates the verdict types, making the purpose unmistakable.

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?

Gives a clear when-to-use instruction: "Use whenever the agent needs to check whether something a user said is factually correct." It also explains that the same tool handles both structured financial claims and open-domain claims, and notes it replaces 4–6 sequential calls. However, it does not name alternative sibling tools or explicitly state when *not* to use it, so it falls short of full exclusion guidance.

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