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

With no annotations provided, the description carries the behavioral disclosure burden. It does this well by revealing that both user and system apps are included, non-app packages are excluded, and includeNonLaunchable changes the result to a raw package list. The concrete Pixel example adds practical calibration; only minor behaviors like output shape remain unspecified.

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 tightly structured: the core definition comes first, followed by an illustrative exclusion example, then flag usage. Every sentence contributes meaningful operational guidance, and there is no redundant restatement of the tool name or schema.

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 relatively simple list tool with well-documented parameters, the description is nearly complete. It covers what is returned, what is filtered out, and how to broaden or narrow results. It lacks an explicit statement of the return value format (e.g., package names vs. app names), but this is a minor gap given the tool's purpose.

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?

The input schema already documents all three parameters with 100% coverage, so the baseline is 3. The description adds value by linking userOnly to 'drop preinstalled apps' and includeNonLaunchable to 'raw package list', which reinforces the semantic distinction and ties each flag back to the app-vs-package concept.

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 identifies the verb 'List' and the resource 'APPS installed on an Android device', then sharpens the definition by including only launcher-icon-bearing apps and giving concrete examples like Settings and Chrome. It also contrasts apps from non-launchable packages, making the tool's exact scope unmistakable and differentiating it from package-listing operations.

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 clear operating context: it explains what counts as an app, what is excluded, and how the flags alter the result. It does not explicitly name an alternative tool or state when-not-to-use this one, so it falls short of full routing guidance, but the boundary is clear enough for an agent to decide when this tool is appropriate.

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