open_app

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It transparently shares that unknown/not-installed apps return a structured APP_NOT_INSTALLED error with a hint, which is valuable beyond the schema. It does not describe success return values, but the output schema is present, and the error behavior is a key transparency win.

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 two sentences, front-loaded with the primary action ('Launch an installed app'), and every sentence earns its place: the first defines the purpose, the second provides essential error behavior. There is no redundancy or fluff.

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 simple tool with two well-documented parameters and an output schema, the description covers the core purpose and a likely failure mode. It does not explain successful return behavior, but the output schema can handle that, and the device parameter's semantics are fully covered by the schema. Overall, it is complete enough for an agent to select and invoke correctly.

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 100%, with both parameters (app_name and device) clearly explained. The description's mention of 'friendly name or package name' is reflected in the schema example, so it adds little new parameter-level meaning beyond what is already in the structured data.

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 'Launch an installed app by friendly name or package name,' using a specific verb and resource. It is easily distinguished from sibling tools like tap, swipe, and open_settings, which handle UI interactions or specific settings rather than general app launching.

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 gives clear context that this tool launches apps by name and handles unknown app errors, implying its use for opening applications. However, it does not explicitly mention when to prefer this over alternatives like open_settings or provide exclusion criteria, so it falls short of explicit when/when-not guidance.

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