adb_launch

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. The description says 'launch' which implies a side-effecting action, but it doesn't state whether this replaces the current activity, requires specific permissions, what happens if the app is already running, or what the typical output/return looks like. With zero annotation coverage for a state-changing tool, this is a significant gap.

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 sentence with minimal waste. The example package name adds useful concrete context. It's appropriately brief for a simple tool, though it could argue for slightly more detail about serial handling or output without becoming bloated.

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?

This is a side-effecting tool (launches an app) with no annotations, no output schema, and only 50% parameter documentation. The description explains the core action but omits crucial context: prerequisites (device connected via adb), error handling (app not found), idempotency (what if already running), and return value semantics. For a tool that mutates device state, more completeness is warranted.

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 50%: the 'package' parameter has no description in the schema, while 'serial' has one. The description adds value by explaining that 'package' is a package name and giving an example (com.spotify.tv.android). However, it doesn't add meaning beyond what the parameter name implies, and the serial parameter's semantics ('omit if only one device') are covered by the schema, not the description.

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 uses a specific verb+resource combination: 'Launch an app by package name'. This clearly states what the tool does and includes a concrete example package name. It distinguishes from siblings like adb_start_intent (which launches intents, not apps) and adb_current_app (which queries current app). However, it doesn't explicitly differentiate from adb_start_intent.

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 no guidance on when to use this tool versus alternatives such as adb_start_intent, adb_open_url, or adb_key. There's no mention of prerequisites (e.g., app must be installed, device must be connected), no exclusion scenarios, and no context for when launching via package name is preferred over other launch methods. The usage context is entirely implied.

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