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 covered. The description adds the metric definition (share of cohort returning in later periods) and the identify scope, which is meaningful context. However, it doesn't disclose granularity limitations, minimum cohort size, or return format.

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?

Single sentence, front-loaded with the core concept and metric definition. No wasted words. Could be slightly richer but is efficient for its scope.

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 read-only analytics tool with no output schema, the description covers the metric but omits the shape of the return (cohort matrix? time series?), defaults for unit/timezone, and any constraints on data availability. An agent can call it, but won't fully know what to expect back.

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 coverage is 67% – site_id and timezone have descriptions, but 'unit' (enum day/week) has no schema description. The description implies daily/weekly cohorts via 'daily or weekly cohort,' which compensates for the unit enum, but doesn't clarify defaults or how timezone interacts. Baseline 3 is appropriate given partial coverage.

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 verb+resource: cohort retention analysis for identified users, with the metric definition (share of cohort that returned in later periods). It clearly distinguishes from siblings like get_overview or get_breakdown, though it doesn't explicitly name an alternative. The qualifier 'identified users (pagelens.identify)' is useful scoping.

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?

No when-to-use guidance. The description doesn't say when to pick this over get_overview, get_breakdown, or list_users, nor does it mention prerequisites like needing identified users via pagelens.identify. An agent must infer context from the name alone.

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