launch_app

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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: each app runs in its own display/window, returns an instance id, and Chromium gets special handling. This is good transparency for a launch tool.

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 concise with two sentences. The first sentence gives the core purpose, and the second adds important details. No redundancy, but could be more structured.

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?

With 3 parameters (1 required) and no enums, the description does not fully explain all parameters. It covers command well, but name and size are omitted. Output schema exists but does not relieve the description from explaining parameter semantics. Overall adequate but with gaps.

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 add meaning. It only explains the 'command' parameter with examples. The 'name' and 'size' parameters are not mentioned, leaving their purpose and usage unclear.

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 clearly states the tool launches a GUI app in a new Xephyr display and returns an instance id. It distinguishes from sibling tools like click, type_text, etc., which are all UI interaction tools, not launching tools.

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 provides examples of valid commands (chromium, xterm, gimp) and mentions automatic flags for Chromium. It implies usage for launching GUI apps but does not explicitly state when not to use it or suggest alternatives.

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