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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description usefully adds that results come from a real algorithm engine rather than LLM generation, which speaks to determinism/trustworthiness, but it omits the randomness/seed behavior and whether the test is one- or two-sided.

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?

Three short segments, front-loaded with the tool's identity and immediately followed by usage conditions and the return value. The bracketed 【置换检验】 label duplicates the title slightly but is not wasteful.

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?

For a 3-parameter tool with a fully documented schema, most of what an agent needs is present, and the description names the returned statistic despite there being no output schema. However, it says nothing about result interpretation (one- vs two-sided), reproducibility, or how small-sample behavior is bounded, which matters for a statistical procedure.

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?

With 100% schema description coverage, the baseline is 3; every parameter (group1, group2, n_perm) is already documented in the schema. The description adds no extra meaning about input format (string arrays of numbers) or how n_perm trades accuracy against runtime.

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 statistical procedure (置换检验 / permutation test) and states the output (置换 P 值), which clearly distinguishes it from siblings like act_tukey_hsd, act_dunn, or act_two_way_anova that perform parametric or rank-based comparisons. It never names a sibling explicitly, so the differentiation is inferential rather than spelled out.

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 gives concrete selection criteria: use when data violates t-test assumptions, when samples are very small, or when an exact non-parametric permutation test is needed. That is clear when-to-use guidance, though it does not state when NOT to use it or point to a specific alternative tool.

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