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

Beyond the annotations (readOnly, openWorld, idempotent), the description discloses critical behavioral traits: the meaning of 'could_not_verify' (check did not happen, carries verification_error, must not be treated as evidence) and the distinction between 'unsupported' and other verdicts. It also explains the dual-path routing (financial vs. general) and that it returns a citation with the actual value, which are 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 longer than typical but every chunk serves a purpose: query examples, usage context, dual-path explanation, return value enumeration, error handling caveat, and efficiency rationale. It is front-loaded with the core purpose and examples. The only minor redundancy is the long list of query phrasings, but these aid matching, so the size is justified.

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 carries full responsibility for explaining return values, which it does thoroughly: it lists all six verdicts, notes the citation, and explains error semantics. It also covers the two main use cases (financial and other) and the unsupported/could_not_verify distinction. The complexity is moderate and the description leaves no critical gaps.

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 description adds significant meaning to the parameters beyond the schema. For tolerance_pct, it explains how to use it for hallucination detection and that it overrides the implied tolerance, capping at 5 by default. For claim, it provides usage examples and clarifies it is natural language. The schema coverage is 100%, but the description enriches the parameters with practical guidance, exceeding the baseline of 3.

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 begins with a clear verb-focused statement ('fact check', 'verify the claim') and specifies the resource: 'natural-language claim verification against authoritative sources'. It also distinguishes from sibling tools by explaining it combines multiple steps (NL parsing → entity resolution → data lookup → comparison) into one call, making it unique among related tools like ask_pipeworx_grounded or 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?

The description explicitly states when to use the tool: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also clarifies that financial claims use a fast path and other claims fall through to a grounded pipeline, giving context for expected behavior. However, it does not explicitly name alternative tools or state when NOT to use it, only implying it replaces sequential calls.

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