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 structurally. The description adds that results are PCA scores and explained variance, but says nothing about preprocessing/scaling assumptions, minimum sample requirements, or input orientation for the nested matrix.

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?

A compact, front-loaded metadata line with USE WHEN and RETURNS before the alias list; no filler prose. The ALIASES string is long and mostly redundant keyword padding, but it is placed last and does not obscure the actionable content.

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 two-parameter statistical tool with annotations covering safety and no output schema, the description does cover the purpose and the return concept. It still leaves gaps an agent would want: expected matrix orientation, whether 'groups' is required for coloring only, and what happens with missing values or too few samples.

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 coverage is reported at 100%, so the baseline is 3 even though the description itself says nothing about 'data_json' or 'groups'. The schema labels are terse ('代谢物矩阵', '分组标签') and the nested object shape is undefined, so the description could have added real value here but does not.

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 name plus the USE WHEN clause conveys a specific analysis: unsupervised PCA on a metabolomics matrix, aimed at sample separation and outlier detection. The parenthetical '(unsupervised)' implicitly separates it from supervised siblings such as metabolite_plsda, though no sibling is named explicitly.

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?

USE WHEN gives a concrete triggering scenario ('sample separation / outliers in metabolomics') and a method qualifier ('unsupervised'), which is enough for an agent to prefer it over plsda or volcano-style tools. There is no explicit when-not guidance or named alternative, which keeps it out of the top band.

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