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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so well. It discloses the permanent/destructive nature, the side effects (tenant disabled, Stripe subscription canceled, key invalidated), idempotency behavior, and what is NOT affected (historical usage/signup records remain for audit). This is exactly the kind of context an agent needs before invoking a destructive self-service operation. It could add a note about whether the action is reversible, but the word 'permanently' and the comparison to admin-disabled tenants strongly imply irreversibility.

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 dense but well-organized: it front-loads the core action and effects, then covers idempotency and audit retention. Every sentence earns its place, and there is no filler or repetition of schema content. The structure makes it easy for an agent to parse the critical facts quickly.

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 destructive, irreversible self-service action with no annotations and no output schema, the description is remarkably complete. It covers the action, side effects, idempotency, and what is preserved. The only minor gap is that it doesn't describe the success response shape or whether the caller should expect a confirmation object, but since there is no output schema and the error behavior is described, this is a small omission. Overall, an agent has enough to invoke this tool correctly and understand the consequences.

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 schema already documents the single parameter (tenant_key) and its optionality. The description adds meaningful context by explaining when the parameter is required (when no Authorization header is present) and the precedence rule (header wins). This goes beyond the schema's description and helps the agent decide whether to pass the parameter. A 4 is appropriate because the description adds value, though the schema already covers the basics.

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 states a specific verb ('close'), the resource ('your own account'), and enumerates the concrete effects: disables the tenant, cancels the Stripe subscription, and stops key authentication. It also explicitly distinguishes this from admin-disabled tenants by noting it is the same behavior, and the idempotency note clarifies what happens on repeat calls. This is unambiguous and clearly differentiated from siblings like host.key_rotate or billing.status.

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 description clearly implies when to use it: when a user wants to permanently close their own account, and it contrasts with admin-disabled tenants. It does not explicitly name alternative tools or say 'use X instead', but the context is strong enough that an agent can infer this is the self-service offboarding tool. The idempotency note also guides behavior on repeated calls. A small gap: it doesn't explicitly state when NOT to use it (e.g., if the user only wants to cancel billing without closing the account).

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