verify_subset_win

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds behavioral context beyond annotations by specifying that it applies a multiple-comparisons correction and expects a raw (uncorrected) p-value. It does not mention edge cases or return format, but the annotated safety profile plus the statistical behavior described is sufficient.

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 two sentences, no filler, and front-loads the core purpose. Each sentence adds useful information: the first explains what the tool does, the second tells the user what inputs are needed. It is appropriately sized for the tool's simplicity.

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?

The tool is low-complexity, with full schema coverage, a rich annotation set, and an output schema present. The description sufficiently explains the scenario and inputs, and the presence of output schema covers return-value expectations. It does not explain the statistical method (e.g., Bonferroni vs FDR), but that is likely not necessary for an agent to invoke the tool correctly.

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 descriptions already provide full coverage (100%) for all three parameters, including the meaning of p and n_tests. The description repeats the instruction to pass p and n_tests but does not add new semantic detail beyond what the schema already explains. This aligns with the baseline score of 3 for high schema coverage.

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 what the tool does: it corrects a 'we lead on subset/metric/checkpoint X' claim for the number of comparisons (look-elsewhere effect). It explicitly mentions passing raw p-value and number of tests, making the operation unambiguous. This distinguishes it from sibling verification tools by focusing specifically on subset/metric/checkpoint multiple-comparison correction.

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 provides clear context for when to use the tool: when you have a subset/metric/checkpoint claim and need to correct for multiple comparisons. It does not explicitly name alternatives or exclusions, but the scenario is well-defined, so an agent can infer when this tool is appropriate. No when-not-to-use guidance is given, preventing a 5.

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