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

Beyond the annotations (readOnly, idempotent, etc.), the description discloses nuanced behaviors: the distinction between 'could_not_verify' (check did not happen) and 'unsupported' (no source found), inclusion of verification_error details, and the use of verbatim evidence. This clarifies how to interpret results and avoids false conclusions, going far beyond what annotations convey.

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, front-loaded with trigger phrases and a clear purpose. Each section (when to use, pipeline behavior, output semantics, error handling) earns its place; however, it could be slightly tightened by trimming the repeated claim examples, though they do help clarity.

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?

For a tool with no output schema, the description thoroughly covers return values (verdict list, actual value with citation, reasoning), error semantics, and the fallback pipeline. It also explains how this tool integrates with others ('Replaces 4–6 sequential calls'), making it self-sufficient for an agent to invoke 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?

The schema already provides full descriptions for both parameters, but the tool description adds crucial context for tolerance_pct, such as overriding implied wording, its use in hallucination detection, and the default cap at 5%. This enriches parameter understanding beyond the schema alone.

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 a specific verb+resource: 'natural-language claim verification against authoritative sources', and opens with common query phrases that clarify its purpose. It clearly distinguishes itself from siblings like ask_pipeworx or deep_research by focusing on fact-checking with a verdict output.

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 'Use whenever the agent needs to check whether something a user said is factually correct', and explains the two distinct paths (SEC EDGAR fast path vs. grounded pipeline) with a fallback rule. It also notes that this tool replaces 4-6 sequential calls, giving strong guidance on when to invoke it over a multi-step approach.

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