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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds value by stating determinism (consistent with idempotency), the paid nature with specific pricing, and the exclusion list for inappropriate use. No contradiction with 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 concise (three sentences), front-loaded with the core action, then adds usage constraints and cost. Every sentence earns its place without fluff or repetition.

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?

With no output schema and no parameter descriptions, the description must fully specify how to call the tool. It omits the format of observations, the meaning of metric_fields, the set of computed statistics, and the return shape. An agent would be uncertain about how to populate the required parameters and interpret the result.

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 0%, so the description must compensate. It only says 'caller-supplied observations and explicitly named numeric fields,' giving a vague hint that metric_fields are names of numeric fields. It does not explain the structure of observations (array of objects with what properties?), how to specify field names, or what statistics are computed. This is insufficient for an agent to correctly construct parameters.

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 a specific action: computes deterministic descriptive benchmark statistics over caller-supplied observations and numeric fields. It also names the domain (dispute provenance / price unknown) and explicitly excludes legal, identity, sanctions, fraud, contractual, and regulatory adjudication, which distinguishes it from sibling benchmark feeds like outcome_assurance and reliability_quality.

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 intended use ('Intended for dispute provenance / price unknown') and explicit exclusions ('Do not use for...'), which tells an agent when not to use it. However, it does not name alternative tools for those excluded use cases, but the exclusion list is sufficient to guide selection among siblings.

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