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

No annotations are provided, so the description carries the full burden of behavioral disclosure, and it reveals nothing. It does not state whether this is a computation, what output format to expect, whether it is read-only, or any edge cases or assumptions.

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 short, but this is under-specification rather than conciseness. It contains no useful content, no structure, and no front-loaded information that would help an agent.

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 annotations, no output schema, and a tautological description, the tool is completely inadequate. An agent cannot determine what inputs are needed, whether they are required, how to format them, or what output to expect. It is indistinguishable from dozens of similar statistical tools.

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?

The description adds no meaning beyond the input schema. The schema's own descriptions ('N to process', 'Value to process') are already vague, and the tool description fails to clarify what 'n' and 'value' represent in a percentile calculation, how they relate, or what data formats are expected.

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 'Percentile: Percentile' is a pure tautology that merely restates the tool name with no verb, resource, or operation specified. It gives an agent no idea what the tool actually computes, especially given the ambiguous parameters 'n' and 'value'.

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?

There is no guidance on when to use this tool versus the many sibling tools such as x402-percentile-rank, x402-percentile-rank-of, x402-quartile, or x402-decile. The description provides zero context for selecting this tool over alternatives.

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