computer.launch_application

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

No annotations are provided, so the description must carry behavioral disclosure. It usefully states that launching is 'Subject to security.allowed_applications', which informs the agent of a likely permission gate. However, it does not describe failure behavior (e.g., error on disallowed application, whether it waits for the app to open) or return/acknowledgment semantics.

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?

A single, well-structured sentence front-loads the action and resource, gives concrete examples, and ends with the security constraint. No filler or redundancy.

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, no-output-schema tool with no annotations, the description covers the core invocation: what it launches and what inputs are valid. It could mention what happens when security.allowed_applications blocks the request, but the overall definition is sufficient for correct selection and most likely 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 does by enumerating accepted command forms ('chrome', 'code', a .desktop entry, or a full path'). For a single required parameter, this meaningfully clarifies what 'command' accepts, though it stops short of explaining .desktop entry syntax or path resolution.

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 names a specific verb ('Launch'), a resource type ('GUI application'), and concrete valid inputs ('chrome', 'code', a .desktop entry, or a full path'). This clearly distinguishes it from the sibling interaction/observation tools such as computer.click or computer.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?

The description clarifies when to use this tool: to launch GUI applications, and the accepted command forms are listed. It doesn't explicitly exclude non-GUI commands or name an alternative like a terminal-run tool, but none of the siblings handle launching, so the context is adequately clear.

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