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

Annotations already provide readOnlyHint=true, openWorldHint=true, idempotentHint=true, and destructiveHint=false. The description adds significant behavioral context beyond these: the two processing paths, the verdict taxonomy (with specific meaning of could_not_verify vs unsupported), the inclusion of verification_error, and the requirement to not treat could_not_verify as evidence. This exceeds annotation coverage and gives the agent critical operational knowledge.

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 is dense with essential information. It front-loads with usage examples and purpose, then covers routing, return values, and error semantics. The 'IMPORTANT for callers' note is prominently placed. No filler or redundancy; structure mirrors the tool's two-path logic.

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?

Despite lacking an output schema, the description fully specifies return values (verdict, actual value with citation, reasoning), explains all verdict types, and details the error-handling semantics for could_not_verify. It covers both fast-path and fallback scenarios. For a complex tool with two routing paths and nuanced error states, this is complete and self-sufficient.

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 both parameters are documented. The description adds value by explaining tolerance_pct's overriding behavior, its range, and default cap, plus practical guidance for hallucination detection. It clarifies the claim parameter with multiple examples. This goes beyond the schema baseline, but still leaves the exact interplay between tolerance and claim wording implicit, so not a perfect 5.

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 starts with concrete user utterances ('Is it true that…', 'fact check') and then explicitly states its core function: natural-language claim verification against authoritative sources. It clearly distinguishes itself from sibling tools by explaining it replaces 4–6 sequential calls and by specifying the two routing paths (SEC EDGAR fast path and grounded pipeline).

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 gives explicit when-to-use guidance: 'Use whenever the agent needs to check whether something a user said is factually correct.' It further differentiates between company-financial claims (fast path) and other claims (grounded pipeline), and includes an important caller note about could_not_verify vs unsupported, which prevents misinterpretation. This is a model of usage clarity.

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