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

No annotations are provided, so the description carries the full burden. It discloses key behaviors: force-stops the app first for cold launch, uses the per-app LocaleManager API via a specific command, override persists until cleared/uninstalled. It complements the device_clear_app_locale sibling by implying how to reverse this. Good disclosure without annotations.

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?

Three sentences, dense with useful information: what it does, prerequisites, mechanism, side effects, and persistence. Every sentence earns its place. Could be slightly tightened but is appropriately front-loaded with the core purpose first.

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 3-parameter launch tool with no output schema, the description covers prerequisites, mechanism, side effects (force-stop, persistence), and reversal path (device_clear_app_locale exists as sibling). The behavior is clearly specified including what the override persists through. No output schema needed since launch tools typically return simple success indicators.

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 100%, so the schema documents all 3 parameters (udid, packageName, locale with an example 'fr-FR'). The description adds value by explaining the locale parameter is BCP-47 format implicitly through the schema example and explains the broader mechanism, but doesn't add much parameter-specific semantics beyond what the schema provides. Description mentions the persistence side-effect which contextualizes locale.

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 states the verb (Launch), resource (Android app), and the specific scope (forced into a language/locale without changing system settings). It distinguishes this from siblings like device_launch_app (plain launch) and device_set_device_language (changes system language) and ios_launch_app_in_language (iOS counterpart). The platform and API details are explicit.

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 clearly specifies Android 13+ (API 33) as a prerequisite and mentions it's distinct from changing system settings, implicitly contrasting with device_set_device_language. It notes the force-stop behavior but doesn't explicitly name alternative sibling tools or give when-not-to-use conditions beyond the OS version constraint.

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