launch

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

With no annotations to lean on, the description carries real weight: it discloses that the view switches to `workspace` before launching, that it blocks up to `wait_for_window` seconds (capped at 60), and that it focuses and reports the resulting window. It omits what happens on timeout or when no window appears, and does not characterize the arbitrary-command execution side effect.

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?

Three short sentences, front-loaded with the verb and examples, then the window/workspace behavior. Little waste, though the parenthetical max-60 note is slightly buried in the middle sentence.

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?

Output schema exists so return values needn't be explained, but for a 4-parameter process-launching tool with zero annotations, gaps remain: `cwd` semantics, timeout behavior, and whether the launched process is detached or blocks the session are all unaddressed.

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 0%, so the description must compensate. It adds genuine meaning for `workspace` (the view switches there first, otherwise current) and `wait_for_window` (seconds, max 60, window is focused and reported), but `cwd` is never mentioned and `command` is only illustrated by examples rather than defined.

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?

Specific verb and resource: 'Run a shell command on the agent desktop', reinforced with two concrete examples ('xterm', 'firefox --new-instance'). It is not differentiated from the sibling `bash`, which is the obvious competing choice for running a command; the agent is left to guess why one exists over the other.

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 examples and the window/focus behavior imply this is for launching GUI applications on the remote desktop rather than generic scripting, but that is inference. There is no explicit statement of when to prefer this over `bash`, nor when not to use it (e.g. non-GUI or long-running commands).

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