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

Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=false, so the safety profile is covered. The description adds a genuinely useful trait: results come from a real computation engine, not an LLM. It says nothing about failure modes (for example, a single group or non-numeric times), so the behavioral disclosure stays thin.

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?

Two short clauses, bracketed title first, then the return statement — every line carries content and the key information is front-loaded. The repeated title phrase is slightly redundant with the annotations' title.

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 description does at least tell the agent what comes back (KM curve plus median survival), which is valuable. It still omits output shape, how grouping affects the result, and edge-case behavior, so it is adequate rather than complete for a statistical tool.

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 100%, so times, events, and groups are already documented, and the description adds no further meaning about formats, event coding, or what happens when groups is omitted. Under the stated baseline, a 3 is the correct score when the schema does the work.

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 method (Kaplan-Meier) and names the deliverables (KM curve and median survival), so what the tool does is unambiguous. It doesn't name the sibling it is meant to replace (act_survival_analyze / act_animal_survival), so the separation is implied rather than stated.

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?

"用户只要 KM 曲线和中位生存，不做多因素" states a selection condition: use this when only univariate KM plus median survival is needed rather than a multivariable model. That is real guidance, but the alternative tool is never named and no prerequisites or exclusions for the data are given.

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