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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive. The description goes beyond by explaining verdict semantics (confirmed, refuted, etc.), warning that could_not_verify means the check did not happen and must not be treated as evidence, and that unsupported means no source was found. This is critical behavioral context that annotations do not provide.

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 dense but every sentence earns its place: trigger phrases, usage guidance, routing logic, return values, error semantics, and value proposition. It is well-structured, starting with the most critical cue phrases and ending with the efficiency benefit, with no fluff or repetition.

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 fully explains what the tool returns: a verdict, the actual value with citation, and reasoning. It covers edge cases (could_not_verify with verification_error, unsupported), both processing paths, and parameter overrides. This is a complete description for an agent to confidently invoke the tool.

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?

Although schema coverage is 100%, the description adds substantial meaning to tolerance_pct by explaining that it overrides wording-implied tolerance and suggesting 1–2% for hallucination detection. It also provides concrete claim examples for the claim parameter, going well beyond the schema's basic 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 a specific verb and resource: it verifies natural-language factual claims against authoritative sources. It lists concrete trigger phrases ('fact check', 'verify the claim that…', 'did X really…') and distinguishes two paths (structured SEC EDGAR for company-financial claims, grounded pipeline for all other claims), which separates it from sibling tools like resolve_entity or ask_pipeworx.

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 gives routing guidance (company-financial vs. other claims) and explains that it replaces 4–6 sequential calls, implying it is the single call for claim verification. It does not name alternatives directly, but the usage context is unambiguous.

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