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

Annotations already declare readOnly=true, non-destructive, closed-world, so the safety profile is covered. The description adds a genuinely non-obvious methodological rule — 'Only users who have had the full window are counted' — which affects how results should be interpreted. It does not state response shape, but the metric framing implies a rate.

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?

Three short sentences with the core metric definition front-loaded and no filler. The phrase 'within N days' is slightly ambiguous against the two distinct day parameters, a minor clarity cost.

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 and 0% schema description coverage on three parameters, so the description bears most of the load. It adequately conveys the metric and one edge rule, but leaves cohort_days undefined and says nothing about return value format or units.

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 0%, so the description must carry parameter meaning, and it does well for 'event' (action-specific vs any activity). However, 'cohort_days' is never mentioned and 'within_days' is only obliquely referenced as 'N days', leaving the agent to guess which parameter controls what. Partial compensation only.

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 a specific metric verb ('Share of recent signups who did something within N days of joining') and explains the two measurement modes, which is enough to separate it from siblings like get_retention or get_active_users. It doesn't explicitly name the neighboring tools it differs from, so it stops 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?

It tells the agent how to measure a specific action (pass an event name) versus generic activity (omit it), which is useful in-context guidance. It never states when to reach for this instead of get_retention, get_growth_report, or get_active_users, and gives no when-not guidance.

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