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

The annotations already declare readOnlyHint=true, so 'Read-only' in the description is redundant. The eligible-vs-rate explanation is genuine added value beyond the annotations: it discloses that recent hires are excluded from a maturity window rather than counted as retained, which prevents a serious misreading of the numbers. What's missing is any mention of how the cohort window is chosen (defaults, ordering, whether partial months appear).

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?

Front-loaded with the metric definition, then the sibling distinction, then the interpretive caveat: a sensible order with little padding. 'Read-only' duplicates the readOnlyHint annotation and could be dropped, but no sentence is wasted overall.

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?

The metric semantics (day 30/60/90/180, eligible vs rate) are covered well enough that no output schema is needed to understand the return. However, a 4-parameter tool with zero schema description coverage leaves the agent guessing on parameter formats, and nothing is said about defaults or whether filters apply to the hiring cohort or the retained population.

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% across 4 parameters, so the description must carry the parameter burden and largely does not. The phrase 'hired in a given month' hints that since/until bound a cohort window, but the string format, inclusive/exclusive behavior, and the meaning of location_id and position_id are left entirely to inference.

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?

Names a specific resource and metric: retention by hiring cohort measured at day 30/60/90/180 for people hired in a given month. It explicitly separates itself from the nearest lookalike, hr_cohort_report, by stating that the sibling measures interns while this measures employees.

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 'employment twin of hr_cohort_report (which measures INTERNS)' line gives the agent a clear rule for choosing between the two. It also tells the reader how to interpret and when to distrust the output ('a cohort whose eligible is far below hired is too young to judge'), but it never states prerequisites, defaults, or what happens when since/until are omitted.

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