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

Annotations already provide readOnly/openWorld/idempotent safety signals; the description adds substantial behavioral context beyond that: the meaning distinction between 'could_not_verify' (check did not happen) and 'unsupported' (no source covered), the verification_error structure, and the routing decision logic. This materially helps an agent interpret results correctly.

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 every sentence contributes: trigger phrases, use case, routing logic, return payload, failure semantics, and a caller warning. It is front-loaded with intuitive calls-to-action and uses clear structure (IMPORTANT) to highlight critical caveats without padding.

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 there is no output schema, the description fully covers the return contract (verdict values, actual value with citation, reasoning) and handles edge cases (could_not_verify vs unsupported). For a tool with high behavioral complexity and two routing paths, it is complete enough for an agent to invoke and interpret correctly without further documentation.

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% for both params, so the baseline is 3. The description adds practical nuance for tolerance_pct (e.g., 'set 1–2 for hallucination detection' and the default cap of 5) and clarifies that tolerance overrides the claim's implied wording, which goes beyond the schema text. Claim examples in the schema are adequate, so extra credit is modest.

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 specifies a distinct verb+resource: natural-language claim verification against authoritative sources, with explicit trigger phrases like 'fact check' and 'verify the claim that...'. It distinguishes itself from likely sibling tools by naming its two routing paths (SEC EDGAR/XBRL for company-financial claims vs grounded pipeline for all else) and by stating it replaces multiple sequential calls.

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 states exactly when to use: whenever the agent needs to check whether a user statement is factually correct, with both routing branches spelled out. It does not name alternative tools or explicit 'do not use' conditions, but the breadth of 'ANY OTHER factual claim' plus the claim-verification framing sufficiently sets expectations.

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