stats.anova_oneway

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

Annotations already cover safety (readOnly, idempotent, closed-world), and the description adds behavioral detail beyond them: Tukey-Kramer handling for unequal group sizes and explicit output precision (F to 6 significant figures, other statistics as 10-digit strings). It does not discuss failure modes such as what error is raised for a group of size 1, 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?

Four compact sentences lead with the purpose, then parameters, then numerical behavior, then the alternative. Every sentence supplies information an agent would otherwise have to guess.

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 an output schema exists, return structure need not be described, yet the precision convention and the Tukey-Kramer variant are still noted. Assumptions, minimum input sizes, and the fallback test are all covered, so nothing essential for correct invocation is missing.

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 burden and largely meets it: groups is explained as a list of per-group Decimal strings with cardinality constraints, alpha as a significance level with default 0.05, and include_tukey with its default True. It does not spell out what include_tukey=false returns, which is the only remaining gap.

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 a specific verb and statistical procedure (one-way ANOVA on group means) plus the appended Tukey HSD pairwise comparison, which distinguishes it from siblings like ttest_two_sample or kruskal_wallis. An agent can identify the tool without opening the 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 assumption preconditions (normality and equal variance) and explicitly routes the agent to kruskal_wallis when those are violated. It also constrains input shape (2+ groups, 2+ observations each), which tells the agent when the tool is callable at all.

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