start_driver

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

With no annotations, the description carries the full burden and does well: it warns that the first run builds the runner and that iOS will prompt for a passcode, which is critical context an agent would otherwise be surprised by. It omits what happens if the driver is already running (no-op vs error) and any timing/timeout expectations.

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 tight sentences with zero waste; the core action is front-loaded and the caveats follow. Nothing is redundant or padding.

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-param tool with no output schema and no annotations, the description covers the essential surprises (auto-start, first-run build, passcode prompt). It could be slightly more complete by stating idempotency behavior when already started or what a successful start means for subsequent UI tools.

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 both 'device' and 'rebuild' are already fully documented in the schema, including device fallback resolution. The description adds no further parameter guidance and doesn't connect the build-on-first-run behavior to the 'rebuild' flag.

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 and resource ('Start the on-device XCUITest driver') and implicitly contrasts with stop_driver in the sibling list. An agent can tell immediately what this tool does and what it targets.

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 parenthetical 'UI tools start it automatically' tells the agent it usually doesn't need to call this explicitly, which is a real usage signal. It stops short of explicitly naming stop_driver or saying when a manual start is warranted (e.g., after stop_driver or before a batch of UI actions).

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