Disconnect device

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

Annotations already flag destructiveHint=true and idempotentHint=true, and the description adds real context on top: exactly what breaks (traffic stops traversing Portveil, VPN protection is lost), what survives (device remains on the account), and that it self-restores on reconnect. It also discloses auth requirements (control-scope token, Portveil-agent device) and mandates user confirmation, none of which the annotations convey.

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?

Four short sentences, each earning its place: effect, consequence, scope, prerequisite. The core effect is front-loaded in the first clause and nothing is padded or restated.

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, idempotent mutation with no output schema, the description covers effect, reversibility, and the human-in-the-loop requirement. It does not say what the call returns (e.g., the resulting device state), which is the only notable omission.

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?

The schema covers the single `device` parameter at 100%, including accepted formats, case-insensitivity, and a pointer to list_devices, so the description has nothing to compensate for. Baseline 3 applies since the description adds no parameter detail of its own.

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?

"Turn off a device's VPN tunnel" is a specific verb+resource, and the follow-up sentences disambiguate it from the nearest siblings: the device is not removed from the account (vs remove_device) and traffic resumes when it reconnects (vs reconnect_device). An agent can distinguish this from every sibling without opening a schema.

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?

It gives an explicit procedural precondition ("Confirm with the user first") and states the key scoping fact ("The device stays on the account"), which implicitly routes removal requests to remove_device. It does not name sibling alternatives outright, so the routing is inferred rather than stated.

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