aua_launch_app

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false; the description adds real value by clarifying that app state is preserved (no force-stop, no data reset) and that the launch happens only once. It omits error behavior when the package is not installed and says nothing about what the optional observation triggers.

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?

A single compact sentence with the scope and the key non-behavior front-loaded; every clause carries information and nothing is padded.

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 core contract is conveyed, but with no output schema and zero parameter documentation, an agent still lacks guidance on the observe modes, on package-name discovery, and on failure modes. For a two-parameter tool with a required free-form-looking package argument, that is a meaningful gap.

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 0%, so the description must carry parameter meaning, and it does not. The 'observe' enum (none/tree/screenshot/both) is completely unexplained — the agent cannot tell what each mode captures or how it affects cost/output, and the package format is only enforced via regex with no guidance.

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 and resource — 'Launch an installed package's launcher activity' — plus scope ('once') and exclusions ('no force-stop or data reset'), which separates it from restart-style behaviors. It does not name a sibling (e.g., aua_apps for package discovery), so it falls short of full differentiation.

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 'once, no force-stop' phrasing implies the use case (bring an existing app to the foreground rather than cold-restart it), but there is no explicit when-to-use-vs-alternatives guidance. Nothing tells the agent how to obtain a valid package name, which the strict pattern makes non-trivial.

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