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

Annotations already declare readOnlyHint=true, and the description reinforces that with 'WITHOUT charging or changing anything' and 'Read-only', adding the key behavioral consequence of no charge. This goes beyond the bare annotation by specificying the practical side-effect-free nature and the preview-only intent. No contradiction with annotations exists.

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 one tight sentence that front-loads what the tool does and its key side-effect-free property, then appends the endpoint for reference. Every word earns its place, and the formatting makes the critical information immediately visible.

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 read-only preview call, the description covers purpose, safety, and the general outcome ('cost/effect'). With no output schema, it could arguably say a bit more about what the preview returns, but the core guidance for correct invocation—no side effects, preview-only—is complete. The nested customize and feature_quantities parameters are documented in the schema, so the description does not need to repeat them.

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 parameters are already well-documented. The description does not add parameter-specific detail, but the baseline of 3 applies because schema carries the burden. It loosely ties customer_id and plan_id to the 'attaching a plan to a customer' idea but offers no additional semantic value.

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 opens with the specific verb 'Preview' and the resource 'cost/effect of attaching a plan to a customer', making the operation unmistakable. It explicitly contrasts with the mutating attach_plan sibling by saying 'WITHOUT charging or changing anything', so an agent can tell this apart at a glance.

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 phrase 'WITHOUT charging or changing anything' and 'Read-only' clearly signal this tool is for inspection before a real action, which implies use when the agent wants to evaluate impact without side effects. It does not explicitly name attach_plan as the alternative for actually changing something, but the sibling list plus the contrast is strong enough to guide selection.

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