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

Beyond the annotations (read-only, open-world, idempotent), the description discloses crucial behavior: the fallback from structured SEC/XBRL to a grounded pipeline, and the precise meaning of ambiguous verdicts like could_not_verify (check didn't happen) vs unsupported (no source found). This is exactly the kind of practical behavioral context an agent needs to correctly interpret results, and it does not contradict the 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 average but well-structured: it opens with recognizable trigger phrases, states the use case, explains the two processing paths, lists the verdicts, and clarifies error semantics. Each section earns its place, though the prose could be tightened to reduce redundancy (e.g., the grounded pipeline explanation is repeated).

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 covers everything needed: the decision logic (which path is taken), the complete set of verdicts, what the return value carries (actual value with citation, reasoning), and how to treat failure cases. It also notes the tool's composability by replacing multiple calls, so the agent understands the full scope and side effects. No significant informational 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 input schema already describes both parameters fully (100% coverage), but the description goes further by explaining the semantics of tolerance_pct in use: how it overrides the claim-wording default, is capped at 5, and should be set to 1–2 for hallucination detection. This adds meaningful guidance beyond the schema's field descriptions.

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 identifies the tool as a claim-verification utility, with specific verb+resource ('validate claim') and a host of natural-language trigger phrases. It also differentiates from generic research tools by noting it replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → comparison), making its scope 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?

It explicitly states when to use the tool: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also describes the two internal paths (SEC fast path for company financials, grounded pipeline for anything else), giving clear context. However, it never mentions when not to use it or names alternative sibling tools, so it lacks explicit exclusion/alternative guidance.

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