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

Annotations declare non-read-only, non-idempotent, non-destructive, but the description adds substantial behavior beyond them: the app is killed first when arguments are supplied, the activation path uses the automation session when available and the direct device transport otherwise, and the argv override lasts only for that launch. Missing are failure semantics (e.g., app not installed) and auth/permission prerequisites.

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?

Front-loads the verb and resource, then layers the activate/relaunch distinction before the argv detail. Dense and mostly waste-free, though the final clause about NSUserDefaults is long and could be tightened.

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 three-parameter mutation tool with no output schema, the description covers mode selection, kill-before-launch behavior, transport selection, and argument lifetime. It does not describe what the call returns (e.g., PID) or error conditions, which are the remaining 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 100%, so baseline is 3, but the description genuinely enriches the `arguments` parameter: it explains that values land in the process argv, that NSUserDefaults reads its argument domain from there, gives concrete examples (["-AppleLanguages", "(fr)"]), and states the override is per-launch only. udid and bundleId are left to the schema.

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+resource ('Launch/activate an app on an iOS device by bundle ID') and immediately splits the two distinct modes of operation (activate vs. cold relaunch). An agent can distinguish this from ios_launch_app_in_language, ios_kill_app, and ios_terminate_app without opening any schema.

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?

Gives explicit conditional guidance: omit `arguments` to activate and preserve state, supply `arguments` to force a cold relaunch. It also explains the underlying rule (launch arguments are ignored on a running process, so the app is killed first). It stops short of naming sibling alternatives such as ios_launch_app_in_language or ios_kill_app.

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