stats.wilcoxon

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

Annotations already declare readOnlyHint, idempotentHint, and closed-world behavior, so the safety profile is covered. The description adds valuable behavioral detail beyond them: output precision (w to 6 significant figures, p as a 10-digit string) and the default tail. It does not discuss edge cases like zero differences or ties, which keeps it short of a 5.

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?

It is dense but every sentence earns its place: the purpose and return values come first, followed by parameter semantics, tail options, precision, and sibling routing. There is no filler or repetition of the tool name.

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 three parameters, an output schema, and read-only annotations, the description covers everything needed to call the tool correctly: input format, the b-omitted branch, tail options, and result precision. No critical gap remains for an agent to make a correct call.

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 carries the full burden and does so: it defines a and b as Decimal string arrays, constrains them to equal length with at least one element, and explains the default-null semantics of b. It also enumerates the tail values (two default, less, greater), which the schema does not do via enum.

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 names the exact test ('Wilcoxon signed-rank'), states both supported cases (paired differences or single-sample location shift from 0), and lists the returned values (w_stat, p_value, n). It also names the sibling it is not (mann_whitney_u), so an agent can distinguish it from the independent-sample test without opening either schema.

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 states the condition for supplying b (paired data of equal length ≥ 1) versus omitting it (a is treated as the differences and compared to 0). It also explicitly routes independent two-group comparisons to mann_whitney_u, giving both when-to-use and when-not-to-use guidance.

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