ACTION_LAUNCH_APP

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

With no annotations provided, the description carries the full burden and does substantial work: it names the output variables, warns that on Android 10+ a background launch may be silently blocked while launch_success still returns true, and explains that launch_has_overlay reflects overlay permission as a background-launch exemption. That is exactly the kind of non-obvious failure mode an agent needs. It stops short of stating required permissions, whether an overlay prompt is triggered, or any timing/latency expectations, so not a 5.

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?

Purpose is front-loaded in the first clause, followed by return values and then the critical Android 10+ caveat — a sensible order. It is compact for the amount of behavioral content packed in, though the doubled period ('。。') and the slightly run-on caveat sentence show minor polish issues.

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?

There is no output schema, and the description compensates by enumerating the four returned variables and their meanings, including the counterintuitive launch_success caveat. Combined with a fully documented six-parameter schema, an agent has enough to call this correctly; only permission prerequisites and failure-handling behavior (beyond on_error) are left unstated.

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 100%, so all six parameters (including the on_error enum and node_timeout_ms default) are already documented in structured form, making 3 the baseline. The description adds only the cross-cutting note that string parameters accept ${var} interpolation, which is genuinely useful but does not deepen any individual parameter's meaning.

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 states a specific verb and two concrete resources: launch an app (package_name) or open a system settings page (intent_action). An agent can immediately tell this is a launch/activation action rather than a query or search. It does not explicitly differentiate itself from look-alike siblings such as ACTION_APP_SEARCH or ACTION_FOREGROUND_APP, which keeps it at 4 rather than 5.

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?

Usage is implied through the two modes ('open app' vs 'open a settings page'), and the schema clarifies that intent_action overrides package_name. However, there is no explicit when-to-use guidance against alternatives — an agent must infer on its own whether to call this versus ACTION_APP_SEARCH, ACTION_GET_APP_INFO, or ACTION_FOREGROUND_APP when it wants to know or confirm the foreground app.

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