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

Beyond the annotations (readOnly, idempotent, non-destructive), the description discloses key behavioral traits: the two-tier routing logic, the exact verdict list, the crucial distinction between 'could_not_verify' (a failure, not evidence) and 'unsupported' (no source), and the inclusion of citations and reasoning. This is rich, actionable context that goes well beyond structured 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 long but information-dense; every sentence earns its place. It front-loads the core purpose with trigger phrases, then covers routing, outputs, and error semantics. It is slightly verbose but never redundant, so it earns a 4 rather than a 5.

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, no output schema, and only two parameters, the description is fully complete. It describes all return values (verdicts, actual value with citation, reasoning), explains failure semantics, and covers the routing logic. An agent has everything needed to invoke it correctly and interpret results.

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% and both parameters already have detailed descriptions. The tool description adds examples of valid claims but doesn't further elaborate on tolerance_pct or claim format beyond what the schema provides. It meets the baseline but does not elevate beyond it.

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 and explicitly defines the tool as 'natural-language claim verification against authoritative sources.' It distinguishes two clear pathways (SEC EDGAR for company-financial claims, grounded pipeline for everything else) and names the return verdicts, making the purpose unmistakable and distinct from sibling research tools.

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 states clearly 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains how different claim types are routed and notes that it replaces 4–6 sequential calls. However, it does not explicitly name alternative tools or state when not to use it, so it lacks a full when/when-not contrast.

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