mann_whitney_u

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. It mentions the test's purpose and domain but lacks details on what the tool returns (e.g., U statistic, p-value, effect size), error handling, assumptions (e.g., independence of samples), or performance characteristics. For a statistical inference tool with zero annotation coverage, this is a significant gap in transparency.

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 a single, efficient sentence that packs key information: the tool name, its statistical purpose, and context. It's front-loaded with the main action and avoids redundancy. However, it could be more structured by separating usage notes or parameter hints, but given its brevity, it earns a high score for conciseness.

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?

Given the complexity of a statistical test, no annotations, no output schema, and 0% schema description coverage, the description is incomplete. It doesn't explain what the tool returns, assumptions, or how to interpret results. For a tool with three parameters and inference purposes, more detail is needed to ensure proper use by an AI agent, making this inadequate.

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 schema only defines parameter types without descriptions. The description adds no information about parameters like 'data1', 'data2', or 'alpha' (e.g., that 'alpha' is the significance level). It partially compensates by implying two independent samples are needed, but doesn't explain parameter meanings or constraints, leaving them undocumented. Baseline is 3 due to the schema's basic coverage, but the description adds minimal value.

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 the tool's purpose: 'Perform Mann-Whitney U test' with the explanation that it's a 'non-parametric alternative to t-test' to 'test whether two independent samples come from same distribution.' It specifies the domain (statistics) and category (inference), making the verb+resource relationship explicit. However, it doesn't differentiate from sibling tools like 't_test_two_sample' or 'wilcoxon_signed_rank', which are related statistical tests.

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 implies usage context by mentioning it's a 'non-parametric alternative to t-test' and for 'two independent samples,' suggesting when it might be preferred over parametric tests. However, it doesn't explicitly state when to use this tool versus alternatives like 't_test_two_sample' or other non-parametric tests in the sibling list, nor does it provide exclusions or prerequisites. The guidance is present but not comprehensive.

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