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

Annotations already establish read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. Beyond that, the description adds genuine data semantics: cohorts are PWA installs within the period, opens are tracked forward to today, and not-yet-reached cells are null rather than zero — important to avoid misreading the matrix. It omits permission requirements and any row/cell limits.

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, front-loaded with the output inventory, then the cohort/null semantics. The metric list is dense but each item maps to a real returned field, and nothing is redundant given the absence of an output schema. Minor cost is that the metric enumeration reads as a crammed list rather than structured output description.

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 effectively serves as the return-value contract, and it does so well by naming every metric group plus the null-cell convention. What is missing for a 60-parameter analytics tool is anything about output shape (matrix dimensions, aggregation rules beyond cohorts) or limits on horizon/cohort count.

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?

With 88% schema description coverage across 60 params, the schema carries parameter documentation and the baseline is 3. The description adds interpretive context only indirectly — the day-N/week-N phrasing hints at the granularity/horizon interplay, and 'cohorts = PWA installs in the period' clarifies the period param — but it never explains filters, defaults, or how filters interact with cohort definition.

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 the resource and enumerates the exact metrics returned (per-cohort day-N/week-N retention matrix, aggregate retention/LTV curve, DAU/WAU/MAU, open rate, CPI/ARPU/ARPPU), so an agent knows precisely what this returns. It does not, however, distinguish itself from siblings such as get_cohorts, get_statistics, or get_push_analytics, which an agent could plausibly confuse it with.

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?

There is no explicit when-to-use guidance, no when-not-to-use, and no named alternative among the many overlapping analytics siblings (get_cohorts, get_statistics, get_report). Usage is only implied by the tool name and the list of metrics, leaving the agent to guess whether this or get_cohorts is the right call.

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