launch_app

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

Annotations provide destructiveHint=false, which the description does not contradict. The description adds value by clarifying idempotent re-launch behavior—important for a launch tool. It doesn't detail startup delays, auth requirements, or background process behavior, but for a tool with good annotation coverage, the additional context about re-launch is sufficient. No contradiction with annotations.

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 a single, well-framed sentence that front-loads the verb and resource. It adds a valuable parenthetical about re-launch without any fluff. Slightly higher for a zero-param tool, though it could be made even more explicit about idempotency (e.g., 'safe to call multiple times').

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?

Given the tool has no parameters, no output schema, and a clear annotation, the description is largely complete. It explains what happens (launch or re-launch) and implicitly requires a prior session. For a simple action with low complexity, this suffices. However, it doesn't mention if launching multiple times spawns duplicate windows or is safe, which would enhance completeness.

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 input schema has zero parameters with 100% description coverage, so the baseline is high (3). The description adds no param-specific info because none exist, but it doesn't need to—the schema fully covers parameters. The description earns a 4 for effectively clarifying the tool's scope (no configuration needed) beyond the empty schema.

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 the application configured for the session, including re-launching if closed. This is a specific verb ('launch') and resource ('application configured for this session'), which distinguishes it from siblings like 'close_app' or 'attach_java_swing'. However, it doesn't explicitly contrast with 'create_session' or 'attach_session', which could be related—leaving slight ambiguity.

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 implies usage context by mentioning the application is 'configured for this session', suggesting it should be used after a session exists. However, it gives no explicit guidance on when not to use it (e.g., if already running) or alternatives among 70+ siblings. The parenthetical about re-launch hints at idempotent behavior but stops short of clear best practices.

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