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 elsewhere. The description adds almost nothing behavioral: 'RETURNS: 拟合优度' is a vague restatement rather than a description of the statistic, p-value, or chosen test, and nothing is said about defaults for the distribution argument or handling of small samples.

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 USE WHEN clause is front-loaded, which is good, but the definition is largely pipe-delimited keyword stuffing: a long bilingual alias list and a near-empty 'RETURNS: 拟合优度' tail that consumes space without informing. Tightening the alias block and replacing the returns line with actual output detail would improve it.

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 statistical test tool with no output schema, an agent needs to know what comes back (test statistic, p-value, selected distribution) and what the dist parameter defaults to; the description supplies neither. The 'RETURNS: 拟合优度' phrase does not substitute for an output description.

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 100%, so the baseline is 3 even though the description never mentions either parameter. The schema descriptions are thin ('一列数值', '分布类型'), and the description does not compensate by noting the default distribution, accepted dist values, or minimum sample size.

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 states a specific analysis (goodness-of-fit / normality test on a data column), which is a concrete verb-plus-resource rather than a restatement of the name. It does not explicitly contrast against fitting-oriented siblings such as ic50_fit or calibration_curve, but the 'is the data normally distributed' framing makes the scope clear enough to distinguish.

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 'USE WHEN' clause gives an explicit trigger: the user asks whether data are normally distributed or which distribution fits. The alias list reinforces likely phrasings. It stops short of naming when NOT to use it or which sibling to prefer for other fitting tasks, so it is clear context without exclusions.

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