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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the agent knows this is a safe, closed-world read. The description adds value by stating the return shape ('customer + the segment metric') and the 180-day dormancy threshold, but does not cover ordering, pagination interaction with limit, or how ties/edge cases are handled.

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, front-loaded sentences with no filler: purpose first, method semantics second, return shape last. Each sentence earns its place, though the phrasing 'Returns customer + the segment metric' is slightly terse/informal.

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 simple two-parameter read-only tool with no nested objects, the description covers purpose, both method modes, a key threshold, and the return payload. With no output schema present, it adequately compensates; only minor details like result ordering are unstated.

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 the baseline is 3, but the description meaningfully enriches the terse schema text by defining what each enum value actually selects for. It adds no syntax beyond the schema for 'limit', but the method semantics go beyond what the schema provides.

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?

States a specific verb+resource ('Segment customers') and then enumerates the two segmentation methods with concrete definitions ('top customers by lifetime collected payments', 'no job in 180 days'). This clearly distinguishes the two modes of operation, though it does not differentiate itself from customer-related siblings such as churn_risk or find_customers.

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?

No explicit guidance on when to use this tool versus alternatives. The method definitions imply the scenarios (high-value vs lapsed customers), but there is no statement of prerequisites, exclusions, or routing against siblings like churn_risk, which targets a similar 'dormant customer' concern.

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