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

Annotations already establish that this is a safe, read-only, idempotent, non-destructive operation. The description adds useful behavioral context beyond that: the data sources (Stripe revenue and AI cost) and the default ordering by least profitable customer.

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 a single tight sentence with no waste, and it front-loads the key metric and ordering. Every phrase contributes useful information.

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?

The output schema exists, and annotations cover safety and idempotency, so the description need not explain return values or side effects. It provides enough context to understand the tool’s purpose, though it could better clarify date-range behavior and limit semantics.

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 67%: start and end are documented as YYYY-MM-DD dates, while limit has no schema description. The description does not explain any parameter, but the remaining schema constraints/defaults make the tool minimally usable, so this is adequate with a clear gap around limit semantics.

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 the resource and calculation: revenue from Stripe versus AI cost per customer, with results ordered least profitable first. It distinguishes the tool implicitly from cost/spend siblings by framing it as margin, though it does not explicitly name alternatives.

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?

Usage is implied by the phrase "least profitable first," which suggests this is for identifying low-margin customers. However, the description gives no explicit when-to-use guidance, prerequisites, or comparison to siblings such as get_customer_cost or get_spend.

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