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

The annotations already declare readOnly, non-destructive and closed-world, and the description adds real context beyond them: the concrete outputs (survival curve, median survival, HR, log-rank P) and the claim that computation runs on a real algorithm engine rather than being model-generated, which matters for trusting statistical results. It still omits prerequisites, e.g. that grouping is needed for log-rank or covariates for Cox, and any failure behavior.

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 definition is short, front-loads the method family in a bracketed header, and packs the input scenario and return values into two compact clauses with no filler. It is appropriately sized for a statistical tool, though the bracketed header partially repeats the annotation 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 and six parameters, the description covers the basic purpose and outputs but leaves an important gap: it never states which parameters each analysis_type requires (group column for KM/log-rank, covariate columns for Cox) or how group_col and covariate_cols interact. Sufficient to select the tool, insufficient to invoke it confidently without reading the schema.

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 every parameter is already documented in the schema, and the description adds essentially no parameter-level guidance beyond naming 'HR' and 'survival curve', which loosely maps to covariate_cols and output. Baseline 3 applies where the schema carries the semantics.

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 bracketed title names a specific method family (KM/Cox survival analysis) and the description says what the user must supply (follow-up time and outcome event) and what comes out (curve, median survival, HR, log-rank P). It is clearly distinguishable from most siblings, but it does not differentiate itself from the adjacent act_km_curve tool, which covers overlapping capability.

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 phrase 'user has follow-up time and outcome event, wants survival analysis' implies the trigger condition, but there is no explicit when-to-use versus act_km_curve or act_animal_survival, and nothing tells the agent which conditions call for analysis_type=km versus cox. Usage is inferable rather than stated.

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