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

The description adds substantial behavioral context beyond the annotations' read-only/open-world hints. It discloses the exact verdict types (confirmed, approximately_correct, refuted, inconclusive, unsupported, could_not_verify), explains that could_not_verify means the check failed (not evidence), includes the verification_error structure, and defines unsupported as 'no source exists'. It also reveals routing behavior and the tolerance override, all valuable for correct interpretation of results.

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 well-structured: it opens with trigger phrases, then states the use case, explains routing, return values, and ends with important caller caveats and the efficiency benefit. Every sentence adds unique information, though the single long paragraph with semicolons and dashes could be slightly more scannable. It is appropriately sized for a complex tool with nuanced behaviors.

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 complexity (two routing paths, six verdict types, error semantics) and the lack of an output schema, the description is remarkably complete. It explains return values (verdict, actual value with citation, reasoning), distinguishes edge cases, and integrates with the full usage flow. Combined with the input schema and annotations, an agent has enough to select and invoke this tool correctly without any obvious 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?

Schema coverage is 100%, so the baseline is 3. The description adds meaningful context for 'tolerance_pct' by explaining it overrides the implied tolerance and giving a concrete use case (set 1–2 for hallucination detection). It also provides realistic example claims that illustrate the 'claim' parameter. This extra guidance justifies an above-baseline score.

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's purpose: verifying natural-language factual claims against authoritative sources using specific verb phrases like 'fact check' and 'verify the claim that'. It distinguishes itself from generic research or search tools by explaining the two-path routing (SEC EDGAR for company-financial claims, grounded pipeline for others) and explicitly stating it replaces a 4–6 step sequential process.

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 guidance on when to use: 'Use whenever the agent needs to check whether something a user said is factually correct', with many example query phrasings. It also explains internal routing based on claim type and notes it replaces multiple sequential calls, implying it should be preferred over orchestrating separate steps. However, it does not name any sibling tools as alternatives or state when NOT to use it, so it lacks explicit exclusions.

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