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

Annotations already indicate read-only, open-world, idempotent, and non-destructive behavior. The description adds rich behavioral context: dual verification paths (structured vs grounded), the meaning of each verdict, the distinction between could_not_verify and unsupported, and the requirement not to present could_not_verify as evidence. This goes well beyond what annotations convey.

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 relatively long but well-structured: it starts with user intents, defines the tool, lays out routing, lists return values, and highlights critical caveats. Every sentence adds value, though it could be slightly tighter. It is not overly verbose given the complexity.

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 thoroughly covers expected return values (verdict list, actual value, reasoning), error semantics (verification_error with stage/detail), and fallback behavior. It also explains the tool's position among siblings by replacing multiple sequential steps. Complete for its complexity.

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% with both parameters described, so baseline is 3. The description enhances this by explaining how tolerance_pct overrides the implied tolerance, giving concrete usage examples (e.g., 1–2 for hallucination detection), and clarifying the default cap of 5. This adds practical meaning beyond the schema.

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 states the tool verifies natural-language claims ('fact check', 'verify the claim that…') and specifies it returns a verdict with evidence. It distinguishes itself from sibling tools by describing its role as a complete replacement for 4–6 sequential calls, which is specific and actionable.

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 says 'Use whenever the agent needs to check whether something a user said is factually correct' and provides routing logic (company-financial via SEC EDGAR, other facts via grounded pipeline). It doesn't name alternative sibling tools, but gives clear contextual signals and warns about misusing could_not_verify, which effectively guides appropriate use.

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