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

Annotations already declare readOnlyHint=true and idempotentHint=true. The description adds that it requires mcp:fleet:customer_pii permission, every call is audit-logged, and it's read-only. This adds behavioral context (auth, logging) beyond annotations, without contradiction. It does not explain return format but is sufficient.

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?

The description is two sentences: first sentence details what it does and lists key metrics, second sentence adds usage guidance, permissions, logging, and read-only flag. It's front-loaded with the most important information and every sentence earns its place. No wasted words.

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?

Given the tool's complexity (aggregating funnel stats), the schema is minimal (1 param) and there is no output schema. The description explains what metrics are returned conceptually (conversion rate, etc.) and the purpose. It doesn't specify exact return format, but it's complete enough for an agent to understand the tool's value and operation.

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?

Only one parameter 'days' with full schema description (max 90, min 1, default 30). The description mentions 'last N days, max 90' which reinforces the schema. No additional meaning beyond what the schema already provides. Baseline 3 is appropriate given 100% schema coverage.

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 clearly states it aggregates conversion/drop-off stats for a signup cohort, listing specific metrics like trial active, expired-unconverted, converted-to-paid, conversion rate, etc. It explicitly distinguishes itself from aggregating individual summaries, and the verb 'aggregate' with resource 'signup cohort stats' is specific. It also answers 'where is the funnel leaking' which is a clear purpose.

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 says when to use: to get funnel stats in one call instead of aggregating individual summaries. It mentions the parameter limit (max 90 days). It doesn't explicitly say when not to use or name alternatives, but the context of sibling tools implies it's for a specific purpose. It provides clear context but lacks explicit exclusions.

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