restart_desktop

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

With no annotations, the description carries the full burden and does disclose the critical behavior: everything running on the desktop is killed before a fresh one starts, which signals loss of unsaved app state. It does not cover whether the call blocks until the new desktop is ready, how long it takes, or whether session/auth state survives.

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 sentence, zero waste, with the destructive action front-loaded ahead of the outcome. Every clause earns its place.

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?

The tool is simple and parameterless, an output schema exists so return values need no explanation, and the main risk (all apps killed) is stated. What is missing is timing/synchronicity and whether the call returns before the new desktop is usable — relevant for an agent that must wait afterward.

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 tool takes zero parameters, so there is no parameter semantics for the description to explain. Baseline of 4 applies.

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?

A specific verb pair (kill ... then start) plus the resource (the agent desktop) and its blast radius (every app on it). An agent immediately knows this is a full teardown-and-relaunch, distinct from siblings like launch or close_window. It stops short of naming an alternative for a non-destructive start, so not a 5.

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?

There is no explicit when-to-use or when-not guidance, no prerequisite conditions, and no pointer to launch/close_window as safer alternatives. The destructive framing hints at a recovery/reset scenario, but that is left entirely to inference.

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