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

The description goes beyond the read-only/idempotent annotations by revealing the internal two-path architecture (SEC EDGAR/XBRL for financial claims vs. grounded pipeline for others) and the 'Replaces 4–6 sequential calls' efficiency claim. It also discloses nuanced verdict semantics (could_not_verify indicates check failure, not evidence against the claim) which is critical behavioral context not inferable from annotations. No contradiction 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?

The description is dense but front-loaded with user intent phrases, then logically organizes routing logic, return values, and caller caveats. Every sentence contributes functional information; the paragraph flow is coherent despite length, and it avoids redundancy with the schema.

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 covers return types (verdict enum, actual value with pipeworx:// citation, reasoning), error semantics of verification_error, and the distinction between could_not_verify and unsupported. The two-parameter input is fully covered and the complexity of claim routing is adequately explained, making the description self-sufficient.

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?

Although the input schema already describes both parameters, the description enriches them with concrete examples (e.g., 'Apple's FY2024 revenue was $400 billion') and explains tolerance_pct's overriding behavior, including default cap of 5 and its use for hallucination detection at 1–2%. This adds real guidance beyond the schema's raw type/description.

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 natural-language trigger phrases ('Is it true that…' / 'fact check') and clearly states it performs claim verification against authoritative sources. It distinguishes from generic Q&A by specifying two routing paths (structured SEC EDGAR for company-financial claims, grounded pipeline for all else) and listing the returned verdict types. This clearly differentiates it from siblings like ask_pipeworx_grounded and deep_research.

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?

It explicitly instructs to 'Use whenever the agent needs to check whether something a user said is factually correct,' and clarifies that any non-financial factual claim automatically falls through to the grounded pipeline, so no alternative tool is needed. It also provides critical usage caveats around the could_not_verify verdict not being evidence and unsupported meaning no source found, which are essential for correct invocation and interpretation.

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