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

Annotations already declare this a safe, idempotent read (readOnlyHint=true, destructiveHint=false, idempotentHint=true), so the safety profile is covered. The description adds one genuinely useful behavioral trait: 'Totals only' tells the agent the response is aggregate rather than per-user rows. It says nothing about permissions, defaults, or how the returned periods are shaped.

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?

Two short sentences with the core concept front-loaded and no filler, so nothing needs trimming. The compression is, however, achieved partly by omitting information rather than by efficient phrasing.

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 six-parameter cohort analytics tool with no output schema, the description is thin: it never states what the result looks like (cohort rows by period, which measure is returned) or how 'every' and 'mode' affect output shape. 'Totals only' partially covers the return format but leaves an agent guessing about the response structure.

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% -- mode, every, cohort, return, filters, and website all carry their own explanations, including the enum meanings. The description contributes no additional parameter meaning, so the baseline of 3 applies.

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 defines retention conceptually ('Of the people who first came in a period, how many came back'), which lets an agent infer a cohort-retention computation, but it never states a verb or names the resource explicitly. It also doesn't differentiate itself from siblings like get_breakdown or get_funnel beyond the vague 'Totals only'.

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 and no named alternative. With 24 sibling analytics tools, an agent has to guess whether retention belongs here versus get_breakdown, get_timeseries, or get_funnel; the only hint is the implicit contrast in 'Totals only'.

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