retention_report

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

Annotations already declare this a safe read-only operation, so the description is free to add domain behavior — and it does: incomplete cohort cells are null, weeks are bounded to 0..12, and identities/acquisition history affect accuracy. That caveat about accuracy limits is genuine context an agent could not infer from readOnlyHint/destructiveHint.

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?

Three tight sentences, front-loaded with the output shape before the parameter caveats, with no filler. It is terse to the point that the date-window sentence requires a second read, but nothing is wasted.

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?

An output schema exists, so return structure needn't be re-explained, and the description still covers cohort definition, cell nulls, and parameter precedence. The only substantive omission is the accepted date string format for date_from/date_to, which matters because those parameters are untyped strings documented nowhere else.

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 load, and it does for three of four parameters: event_name's scope ('restricts returning activity, not the first-observed cohort definition') and the days vs date_from/date_to precedence rule are both meaningful. It still never gives the expected date string format, which is the one remaining gap.

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 states a specific resource and shape: 'Weekly first-observed visitor cohorts, weeks 0..12', which tells an agent exactly what kind of report this produces. It is distinct from siblings like funnel_report or breakdown by virtue of the cohort/retention framing, though it never names an alternative to differentiate 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 real invocation guidance for parameters (use date_from/date_to together, otherwise days determines the window; event_name restricts returning activity), but never says when to reach for retention_report versus funnel_report, compare, or breakdown. Usage is implied by the report type rather than stated as a selection rule.

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