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

Annotations already indicate readOnly/openWorld/idempotent safety, but the description adds crucial behavioral context: the dual routing paths (SEC XBRL vs grounded pipeline), the full set of verdicts, the presence of verification_error for could_not_verify, and the fact that unsupported is distinct from refuted. This goes well beyond annotations and gives a complete picture of how the tool behaves.

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 fairly long but well-organized: begins with trigger phrases, then states when to use, describes the two paths, lists return values, and provides an IMPORTANT caveat. Each sentence carries meaningful information; it is dense but not wasteful, though slightly verbose for a tool with only two parameters.

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 tool's complexity (dual routing, multiple verdict types, error semantics), the description is remarkably complete. It explains the return structure (verdict, value, citation, reasoning), distinguishes between could_not_verify and unsupported, and notes what the tool replaces. No critical behavioral aspects are left to inference.

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 descriptions for both claim and tolerance_pct. The description adds value by explaining how tolerance_pct interacts with claim wording, its default cap of 5, and a specific use case (set 1–2 for hallucination detection). It also clarifies that claim is a natural-language factual claim, reinforcing the schema examples without redundancy.

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's function: natural-language claim verification against authoritative sources, with explicit trigger phrases and examples. It distinguishes between company-financial claims routed to SEC EDGAR and other claims falling through to a grounded pipeline, setting it apart from sibling tools like ask_pipeworx_grounded.

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 gives explicit usage guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also clarifies when NOT to use it by explaining that could_not_verify means the check didn't happen, and unsupported means no source exists, preventing misinterpretation. It even says the tool replaces 4–6 sequential calls, implying it should be preferred over a multi-step pipeline.

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