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

Goes well beyond destructiveHint=true by naming exactly what is destroyed (webhook removed, stored key deleted) and the downstream consequence (card checkout disabled). It also discloses the confirm-gated preview-then-execute protocol, which is the key behavioral trait an agent must know before calling a destructive tool.

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?

One front-loaded sentence carrying the action, its side effects, and the gating rule; the parenthetical keeps the confirm protocol from diluting the main clause. No wasted text.

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 destructive teardown with annotations already flagging destructiveness and no output schema, the description supplies everything an agent needs: what is removed, the user-facing effect, and how to actually execute it.

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?

With a single parameter at 100% schema coverage, the baseline is 3, but the description reinforces the semantics of `confirm` in behavioral terms ('previews until confirm: true') rather than just restating the default. Minor value added beyond the schema.

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 concrete verb and resource ('Remove the webhook from the coach's Stripe account and delete the stored key') plus the user-visible outcome ('card checkout turns off'). The provider name alone separates it from disconnect_my_razorpay and disconnect_google_calendar, so an agent can route without opening schemas.

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 outcome clause ('card checkout turns off') implies this is the teardown path for the Stripe integration, and the confirm-gating note tells the agent how to invoke it. However, it never states when to prefer this over connect_my_stripe / get_payment_connections or what preconditions must hold (e.g. no active subscriptions).

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