Retention curves

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds the endpoint path and the bundle-naming gotcha, but says nothing about request charging, pagination, or the shape/width of results (which the schema hints at only via the fields and format params).

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 sentences, zero padding, with the core capability front-loaded and the constraint warning immediately after. Every clause carries information the agent needs.

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 an 11-parameter tool with no output schema, the description covers the highest-risk pitfall (bundle naming) but omits the semantics of the return data and the interaction between breakdown, regions and format. Adequate to invoke correctly, not complete.

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 73%, so most parameters are self-documented, and the description adds genuine value on 'bundle' by warning that the bare value 'retention' is rejected. It does not clarify the other ten parameters (regions, breakdown, id_type interplay), so it stays at the baseline for a mostly-documented schema.

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?

It names the specific resource (cohort retention curves) and the three bucketing options, plus the underlying endpoint, so an agent can tell it apart from sibling tools like app_active_users or app_estimates. It lacks an explicit verb and does not name a sibling it is meant to replace, so it falls just short of a 5.

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 supplies one actionable usage constraint -- that 'retention' alone is invalid and one of the three retention_* bundles must be used -- which prevents a common invocation error. However, it gives no guidance on when to prefer daily vs weekly vs monthly buckets, nor any when-to-use versus the other retention-adjacent siblings.

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