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

The readOnlyHint annotation already establishes this as a safe read operation, so the bar is lower. The description adds the backend endpoint (GET /retention), which is minor context, but says nothing about return shape, pagination, or query limits. With safety already covered by annotations, this is adequately but not richly informative.

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 tight clauses: the retention definition first, the endpoint second. Nothing is wasted and the core meaning is front-loaded. It is brief enough to be efficient without being cryptic.

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 10-parameter tool, the schema fully documents every parameter, and annotations cover the safety profile, so the description's job is mainly to convey the analytical intent. It does that well, and no output schema exists that would need explaining. It is complete enough to call correctly, though not exhaustively descriptive.

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 all 10 parameters – including the non-obvious born_event, retention_type, and interval semantics – are already documented in the schema. The description adds no syntax, format, or default detail beyond what the schema provides, 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 states a specific analytical operation: cohort retention measuring how many users who did `born_event` returned to do `event` over subsequent intervals. It maps cleanly to the retention concept and the GET /retention endpoint. It does not explicitly contrast itself with siblings like mixpanel_segmentation or mixpanel_query_funnel, so it stops short of full sibling differentiation.

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?

Usage is implied by the retention framing but there is no explicit statement of when to reach for this tool versus segmentation or funnel analysis, nor any exclusions or prerequisites. An agent must infer from the name and description that this is the cohort-retention-report choice.

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