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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds value by confirming no identifiers are read or returned, explaining database aggregation, and disclosing the privacy-driven suppression of small cohorts (<5 signups). This goes beyond the annotations. A slight gap is that the exact behavior when suppression occurs (e.g., does it return null or omit fields?) is not specified, so it is not a 5.

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?

Every sentence earns its place: it defines the output scope, clarifies PII safety, notes consistency with a sibling, explains a critical privacy suppression, and disambiguates from the marketing funnel. The main purpose is front-loaded, and there is no filler or redundancy.

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?

With no output schema, the description lists all returned counts (signups, trials, conversions, etc.), which is essential. It clarifies the funnel stage and mentions the suppression but leaves minor ambiguity about whether suppressed cohorts still return totals or are completely omitted, and the exact definition of 'conversion rate' is not spelled out (though it might be derived from the list). These small gaps prevent a 5, but overall it is quite complete for a simple one-parameter tool.

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 100% for the single 'days' parameter, so baseline is 3. The description adds meaning by linking the parameter to the suppression rule ('widen the window instead'), implying that increasing days can avoid cohort suppression. This provides operational context beyond the schema's plain description, raising the score to 4.

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 (get/retrieve implied) and resource: the signup->trial->paid funnel as counts only. It lists the exact metrics (signups, trials active, trials expired, converted, onboarding completed, conversion rate) and explicitly distinguishes itself from the marketing funnel (fleet_analytics_overview) and names a sibling (fleet_product_funnel_summary) whose definitions it mirrors, making differentiation clear.

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 clear context: use this for product funnel counts without PII, and explicitly points to fleet_analytics_overview for the marketing funnel. It also provides operational guidance for the suppression (widen the window). It does not explicitly list conditions for choosing this over fleet_product_funnel_summary, but the 'counts only' and 'no PII' phrasing implies when it is appropriate. This is strong but not fully explicit.

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