launch_app

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

With no annotations, the description details cold/warm start semantics: fresh=True force-stops and clears in-memory state (back stack, drafts, etc.), while fresh=False resumes existing instance. This reveals important side effects and behavioral traits beyond a simple launch action, though it omits other potential side effects like permission requirements.

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 well-structured: a clear first sentence establishes purpose, followed by a concise Args block. The fresh parameter's detailed explanation earns its place, and there is no redundant filler.

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 covers all parameters, provides usage examples, and addresses the fresh/cold-start edge case. Since an output schema exists, the lack of return-value explanation is acceptable. It is complete for the tool's complexity.

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?

All three parameters (device, package, fresh) receive thorough descriptions: device format ('ADB serial or ios:<udid>'), package examples, and fresh's behavioral impact. This fully compensates for the 0% schema description coverage.

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 opens with 'Launch an app by Android package name or iOS bundle id,' using a specific verb and resource. It clearly differentiates from sibling tools like launch_intent (which launches intents) and force_stop (which stops apps).

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 explicitly instructs 'Use search_apps() to find it,' providing a prerequisite/alternative for locating the package. It also explains when to use fresh=True (benchmarks, fresh flow start, or when current state interferes), but does not explicitly contrast with launch_intent or other alternatives.

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