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

Beyond the annotations (readOnly, idempotent, non-destructive), the description adds useful behavioral context: the computation is 'deterministic', the operation is over 'caller-supplied observations', and it includes pricing information ('x402 price is $0.002 USD per call'), which is important for a paid resource. These details go beyond what annotations convey, though return format and error behavior are not described.

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 three sentences with no filler: the first sentence states the core function, the second scopes intended use and exclusions, and the third gives cost. The most important operational detail is front-loaded, and every sentence earns its place.

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 two-parameter compute tool with safety annotations already covering read-only/idempotent behavior, the description covers purpose, usage restrictions, and cost. However, there is no output schema and the description does not characterize the return value beyond 'descriptive benchmark statistics' – an agent cannot predict the shape or content of the result, which is a meaningful gap.

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?

With schema description coverage at 0%, the description compensates by explaining that the tool works over 'caller-supplied observations' (the observations parameter) and 'explicitly named numeric fields' (the metric_fields parameter), clarifying that the string array should contain names of numeric fields. This adds meaningful semantic guidance that the bare schema does not provide.

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 uses a specific verb ('Computes') with a precise resource ('deterministic descriptive benchmark statistics over caller-supplied observations and explicitly named numeric fields'), which clearly identifies the tool's function. It also distinguishes the tool's domain ('dispute provenance / quality unknown') from the many sibling benchmark feeds, making it easy for an agent to tell them apart.

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 when to use the tool ('Intended for dispute provenance / quality unknown') and gives explicit negative guidance ('Do not use for legal, identity, sanctions, fraud, contractual, or regulatory adjudication'). It does not name a specific alternative sibling tool, so it misses the full 'alternatives' criterion, but the domain scoping is clear enough to guide selection.

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