Panic button

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

Annotations already indicate destructive and open-world behavior, but the description adds valuable context: the confirm=true requirement, the postcondition of nothing remaining billable, and the JSON response shape including next_tool and next_args. No contradiction with annotations.

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?

Two concise sentences cover the action, the prerequisite, and the return format with no filler. The most important information is front-loaded.

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 tool with an output schema and annotations covering safety, the description is complete. It explains the scope, the guardrail, and the response envelope, leaving no critical gap for an agent to call it correctly.

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%, with confirm already described as 'Must be true.' The description repeats this requirement but does not add new parameter semantics beyond what the schema already provides.

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 uses a specific verb, 'Destroys every instance on the account,' which clearly defines the tool's scope and distinguishes it from the sibling destroy_instance. It also states the intended result: confirming nothing is left billing.

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 implies usage for a full account-wide teardown, especially with the title 'Panic button,' but it does not explicitly say when to use this tool instead of destroy_instance or list_instances. There is no direct mention of alternatives or exclusions.

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