list_apps

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

The readOnlyHint annotation already tells the agent this is a non-mutating read, lowering the bar. The description adds a genuinely useful behavioral detail — that launchable scope includes system apps like Settings — which prevents misreading a system app as third-party, but it does not explain the other two scopes or what the response contains.

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?

Two short sentences, front-loaded with the core purpose, with no filler. Slightly redundant phrasing ('packages with their names') costs it the top score.

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 two-parameter read-only tool with no output schema, the definition covers the essentials but omits the semantics of two of three scope values and says nothing about result shape (package list only vs. labels). Adequate but with identifiable gaps.

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 50%: `filter` is documented in the schema, while the `scope` enum has no schema descriptions. The description partially compensates by explaining `launchable`, but leaves `third_party` and `all` undefined, so half of the enum values remain guesswork.

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 names a specific verb and resource ('Installed Android packages with their names'), so an agent knows it enumerates packages rather than acting on one. It does not distinguish itself from likely siblings such as app_info, which probably returns per-package detail, leaving some ambiguity about which to call for deeper information.

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?

There is no explicit guidance on when to choose this tool over app_info, launch_app, or install_apk; the sentence about `launchable` describes a scope value rather than a usage scenario. The agent must infer that this is the discovery/enumeration step before acting on an app.

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