User Retention

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

Annotations already carry the safety profile (readOnlyHint=true, idempotentHint=true, destructiveHint=false), so the bar is lower. The description adds the cohort-based behavioral context — grouping users and tracking returns over periods — which is genuinely useful beyond the annotations. However, it doesn't disclose cohort bucketing granularity (daily/weekly/monthly), default period behavior, or how openWorldHint sampling might affect the numbers.

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 13-word sentence that is front-loaded with the verb and resource, with every word earning its place. It is appropriately sized and readable, though it achieves brevity by omitting usage guidance that other dimensions penalize.

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?

There is no output schema, so the description carries the burden of explaining what the tool returns. It only hints 'how many users return over time periods' — an agent won't know whether the response is a cohort table, a time series, period-over-period retention rates, or how cohorts are bucketed. For a complex analytical tool with 7 parameters and no output schema, this is a real completeness gap.

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%, so the baseline of 3 applies. The description itself adds nothing about parameters — 'over time periods' is the only hint at date usage — but the schema fully documents siteId, date ranges, pastMinutes alternatives, timeZone, and the detailed filters object including the user_id dual-hash note. The schema carries the burden adequately.

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 verb and resource — 'get user retention cohort analysis' — and defines the output: how many users return over time periods. The cohort-retention concept is distinctive enough that an agent can separate it from the 49 siblings (overview, metric, journeys, sessions) without opening the schema. It falls short of a 5 only because it doesn't explicitly contrast with any sibling to reinforce the boundary.

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 description gives zero when-to-use guidance: no exclusions, no alternatives, no context distinguishing it from rybbit_get_overview, rybbit_get_metric, or rybbit_get_journeys. In a crowded 49-tool workspace this is a notable gap — the agent must infer entirely from the tool name that retention is the right choice.

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