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

Discloses behavior the annotations flatten: destructiveHint=true and readOnlyHint=false only say 'this may destroy something', while the description explains that the invocation itself is non-mutating, returns a preview of the would-be change plus a confirmation link, and that only the merchant on that page can actually execute the deletion. That guardrail is exactly the context an agent needs before deciding whether to call it and how to report the result. Nothing here contradicts the annotations — it clarifies a two-step flow the hint flags cannot express.

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?

Purpose and the critical preview/confirmation behavior are front-loaded, which is good, but the 'Money is integer minor units (cents)' sentence is irrelevant to a customer-deletion tool with a single email parameter and reads as boilerplate leakage. That sentence does not earn its place and actively risks confusing the agent about expected inputs.

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 one-parameter mutation tool whose annotations already carry the destructive/idempotency profile, the description covers the essential facts: what happens on call, who can complete the action, and that the customer's orders survive. Minor gaps remain (behavior when the email matches no customer, what the preview contains), and the stray money sentence is noise rather than missing context.

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 100% and the sole parameter's meaning (email as on file; orders are retained, the person is removed) is already fully documented in the schema, so the baseline of 3 applies. The description adds no parameter meaning and instead injects an off-topic 'Money is integer minor units (cents)' line that does not correspond to any parameter.

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 ('Delete a customer') and immediately qualifies it as a deletion-request that returns a preview plus a confirmation link, so the agent knows this is not an immediate hard delete. It does not compare itself to sibling customer tools (customers_change_email, customers_create, customers_lookup), but the resource is unambiguous enough that differentiation is not a real risk.

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 rather than stated: the description explains the workflow (call it, get a preview and confirmation link, then the merchant confirms on the page), which tells the agent when this is the right entry point for removing a customer. It gives no explicit when-not-to-use conditions and never names an alternative path, so guidance remains inferential.

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