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

Annotations already cover readOnlyHint and openWorldHint, and the description adds real value on top: it is display-only, its output is not valid verdict input, and the statement/check URLs are not echoed back (a privacy/echo behavior the agent could not infer). It still doesn't describe the returned quantity or its uncertainty, but the behavioral additions are substantive.

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?

Three tight sentences with the core purpose front-loaded and no filler. The only cost is the broken clause structure in the first sentence, which slightly slows parsing.

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 6-parameter tool with no output schema, the description explains what is computed and what is withheld, but not the return shape (single rate per day? per feature stratum? sample counts?) nor what happens when all-optional features are omitted. Adequate but leaves gaps an agent would want filled.

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?

With only 33% schema description coverage across 6 parameters, the description does enumerate all the feature inputs (check_type, claim_kind, host_class, checks, statement, days) and restates the day defaults. But it adds almost no meaning beyond the schema — the default values and the 'not stored and not returned' note on statement are already in the schema — and gives no guidance on which features are needed or how they combine.

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 resource (a Kaplan-Meier base rate/survival prior) and ties it to a new claim's features, which distinguishes it from siblings like get_track_record and get_decay_index. The sentence is grammatically fragmented ('Given ... the Kaplan-Meier base rate ...') with no explicit verb, but the intent is still readable.

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 'Given a new claim's features' implies this is for prospective/unsubmitted claims, and 'Display only, verdict_input false' tells the agent this output must not be fed into a verdict. However, it never names a concrete alternative (e.g., get_track_record for historical claims) or states when not to call it.

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