launch_app

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

With no annotations, the description carries the full burden. It says nothing about whether the call waits for the app to settle, what happens on a blocked/unknown package, or that the default observe=changes returns a screen diff — behaviorally the most important thing an agent needs to know before calling.

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?

One front-loaded sentence with no filler; the parenthetical 'its launcher activity' efficiently explains the default. Slightly dense but every clause earns its place.

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?

A 5-parameter action tool with no annotations and no output schema needs to explain the observe/settle_ms contract and failure modes; the description covers only the launch target. An agent cannot predict the return payload or error behavior.

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 80%, so parameters are well documented structurally. The description adds one useful mapping (package → launcher activity, activity → specific activity) but says nothing about serial, observe, or settle_ms beyond the 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?

States a specific verb+resource (launch an app) and clarifies the two modes: default launcher activity vs. an explicitly named activity. The 'allowed dev app' phrasing hints at a restriction that separates it from generic launchers, but it never names the sibling it replaces (e.g., open_url, start_emulator).

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?

No statement of when to use this rather than open_url, start_emulator, or list_dev_apps, and no note on what happens if the package isn't 'allowed'. Usage is only inferable from the phrase 'allowed dev app'.

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