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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is fully covered. The description's added value is disclosing the exact computation behind the returned number, which matters because a subtly different retention definition would change interpretation. It does not discuss cost, truncation, or how cohorts with insufficient history are handled.

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?

A single dense sentence that front-loads the metric name and default, then immediately supplies the formula. No filler, no restatement of the 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 implicitly defines the return values (a share per requested day-N), which is the minimum needed. However, for a tool with two undocumented parameters, it leaves the agent guessing about cohort_days and whether values are fractions or percentages — gaps an agent would only discover at call time.

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% for both parameters, so the description carries the full burden. It only partially discharges this: the parenthetical 'default 1, 7 and 30' implies what 'periods' means and its default, but the existence of a 90-day cap and 6-item limit is unmentioned. 'cohort_days' is never referenced at all, even though 'users who joined at least N days ago' hints at the cohort window without naming or bounding it.

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 metric (day-N retention) and defines it precisely: 'of users who joined at least N days ago, the share who were active on or after day N.' That formula distinguishes it from a raw count like get_active_users, though it never explicitly contrasts itself with close siblings such as get_activation_rate or get_growth_report.

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?

There is no when-to-use guidance at all: no statement of what question this answers, no prerequisites (e.g. data volume or cohort size requirements), and no pointer to alternatives like find_inactive_accounts or get_growth_report for related analyses. The agent must infer the use case from the metric definition alone.

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