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

Annotations already establish readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered without the description's help. The description adds a RETURNS line naming the outputs (curve + median survival), which is useful, but says nothing about whether a plot is produced, what test accompanies group comparisons, or what happens when 'groups' is omitted. Listing 'log-rank' among the aliases hints at hypothesis testing without confirming it - mildly ambiguous rather than contradictory.

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 pipe-delimited USE WHEN / ALIASES / RETURNS layout is front-loaded and scannable, with the gating condition appearing before the keyword list. The bilingual title repetition and the long alias list are mild padding, but the alias list plausibly serves retrieval matching, so little is pure waste.

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?

With no output schema, the RETURNS line is the only signal about results, and it is too terse for a statistics tool - it does not say whether a figure, a table of survival probabilities, or confidence intervals come back. For a three-parameter analysis tool whose 'groups' argument changes the analysis performed, the definition is adequate but leaves real gaps about the grouped/log-rank behavior.

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%, with all three parameters documented (随访时间, 事件 0/1, 分组) plus a worked example, so the schema carries the semantics. The description adds no parameter-level meaning - notably it does not explain that supplying 'groups' triggers a between-group comparison or how event coding interacts with times - leaving the baseline score appropriate.

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 resource (KM curve plus median survival) and the Chinese title/aliases reinforce the resource identity. It also distinguishes itself from the Cox/multivariable sibling by scoping to 'no multivariable model', though it never names the competing sibling tools (survival_cox, animal_survival_km) 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: KM curve and median survival only (no multivariable model)' gives an explicit positive condition and an implicit exclusion boundary that steers agents toward the Cox model when adjustment is needed. It stops short of naming the alternative tool or covering the overlapping animal_survival_km sibling, so routing still requires inference.

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