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

Annotations already declare readOnlyHint, so 'Read-only' is redundant, but the description adds real behavioral context: cohort members are excluded from day marks that have not yet arrived rather than counted as losses. That censoring rule materially changes interpretation, though return shape and aggregation behavior remain unstated.

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?

It is front-loaded with the concrete metric definition, then the interpretive rationale, then the censoring rule, then parameters. The retail framing sentence is slightly promotional but still earns its place by conveying usage context.

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 five-parameter reporting tool with no output schema, the description explains what is measured and how censoring works but not what the report returns (fields, grouping, ordering) or how filters combine. It is enough to call correctly but not enough to consume the result confidently.

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 0%, so the description carries the burden, and it only lists names: 'period', program_id, location_id, mentor_person_id, marked optional. 'Period' loosely maps since/until, but no formats, units, or filter semantics are given, and the fact that all are optional merely restates the schema.

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 and metric: intern survival shares by starting-month cohort at day 1/3/7/14/30/60. That definition is sharp enough to separate it from nearby siblings like hr_turnover_report or hr_dropoff_reasons_report, though no sibling is ever named 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?

It gives a clear use case — the most informative report for high-churn retail — and explains the distinction it surfaces: early-vanishing channels versus late-stage shop-level loss. There are no explicit exclusions or named alternatives, so the agent must infer when a different HR report is better.

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