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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and non-destructive. The description adds meaningful behavioral context beyond these: it explains the veredict taxonomy, explicitly warns that could_not_verify means the check did NOT happen and must not be treated as evidence, and distinguishes it from unsupported. It also discloses the routing behavior and the percent-delta math for financial claims. This is rich, safety-relevant disclosure that goes well beyond the 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 every sentence earns its place: it packs trigger phrases, two routing paths, veredict taxonomy, evidence/citation behavior, two critical meaning nuances (could_not_verify vs unsupported), and a value proposition ('Replaces 4–6 sequential calls') into a dense but readable paragraph. It is front-loaded with the most important usage signal (natural-language triggers) and ends with the efficiency note.

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 very thoroughly covers return values (verdict + actual value + reasoning), edge cases (could_not_verify, unsupported), and routing behavior. It also explains how the two parameters interact (tolerance_pct's default and override semantics). Given the complexity of this tool, the description is remarkably complete.

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 description coverage is 100% (both claim and tolerance_pct are documented in the schema). The description adds extra meaning: it explains that tolerance_pct overrides the tolerance implied by the claim wording, gives concrete guidance for hallucination detection (set 1–2), and notes the default cap of 5. The claim parameter is also enriched by showing the natural-language trigger phrases. This goes above the schema baseline of 3.

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 explicit natural-language triggers and a clear verb: 'natural-language claim verification against authoritative sources.' It specifically states what the tool does—check whether a user's factual claim is true—and distinguishes its two execution paths (SEC EDGAR/XBRL fast path for company-financial claims; grounded pipeline for everything else). This clearly differentiates it from sibling tools like compare_entities, resolve_entity, or search_within.

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 when-to-use guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It also explains the routing behavior for company-financial versus any other factual claim, and states what it replaces ('4–6 sequential calls'). It does not explicitly name alternative tools, but the scope of when to use this tool versus doing multi-step lookups is clearly defined.

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