Add device

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

With annotations covering only the generic safety profile, the description carries rich behavioral detail: the private key is generated locally and never shown in the reply, one tunnel file is written per location to a folder, linux devices register themselves and return root commands, and phone_or_computer devices are view-only and cannot be moved remotely. It also discloses the admin-token requirement and slot consumption.

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?

Front-loaded with the core action, then organized by kind, with each sentence carrying distinct information (folder behavior, key handling, admin scope, slot usage). It is long for a single dense paragraph, but almost no sentence is redundant.

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 5-parameter mutation tool with no output schema, the description compensates well: it explains what the tool returns (commands for linux, saved files for phone_or_computer) and the side effects (slot consumption, temp deletion, view-only constraint). An agent has enough to invoke it correctly for either kind.

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 already 100%, but the description adds meaning beyond the schema: it explains the practical consequence of each kind (files written vs commands returned), that temporary_minutes implies auto-deletion, and that the key is never displayed. This goes past a baseline 3 where the schema does the heavy lifting.

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?

Starts with a specific verb+resource ('Add a new device to the account') and then splits the resource into two named kinds (phone_or_computer vs linux_machine) with distinct behavior. It also signals relationship to siblings by noting linux devices 'can then be moved, rotated and switched with the other tools', letting an agent place it against move_device/rotate_device.

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?

Gives clear operational guidance: which kind to pick for a phone/laptop vs a server, that the WireGuard app must import the file to connect, that phone_or_computer needs an admin-scope token, and that it consumes a device slot. It stops short of explicit exclusions (when NOT to use add_device) or naming a sibling alternative for a given scenario.

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