launch_app

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

With no annotations, the description carries the transparency burden and does well: it discloses sandboxing behavior, that commands are parsed with shlex, and that the result is a JSON object with pid, command, and display. Failure behavior and permissions are not covered, but key launch semantics are.

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?

The description is compact and front-loaded: the core action comes first, followed by the key behavioral caveat, examples, return shape, and suggested workflow. It is dense but not wasteful.

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 description provides useful workflow and return info, but it omits the meaning of settle and does not explain how the isolated/real mode is chosen given the schema only exposes command and settle. This leaves a meaningful gap for correct invocation.

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 description coverage is 0%, so the description must compensate. It documents command with shlex parsing and examples, but it never explains the settle parameter, and it introduces isolated/real modes without saying how those modes are selected through the provided schema. An agent cannot fully determine argument semantics.

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 explicitly states it launches an application on the target display and distinguishes isolated vs real modes. This clearly separates launch_app from sibling tools, which are all interaction/inspection operations like click, type_text, and get_ui_tree.

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 explains when isolated mode is appropriate (the only way to put an app on the virtual screen without affecting the host) and gives a follow-up workflow: use wait_window, then get_ui_tree/click. It does not name alternative launch tools, but the context is clear enough.

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