do_steps

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

With no annotations, the description carries the burden and does well: it enumerates the four stop conditions (first failure, blocked step, approval card, app foreground change) and discloses that per-step approvals apply. It does not say whether already-executed steps are rolled back after a stop, nor that actions are irreversible.

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-loaded with purpose and the concrete example, then the mechanics, then the stop and return behavior. Dense but nearly every clause carries information; only the parenthetical example is optional 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 complex, unannotated, output-schema-less batching tool it covers the essentials: how steps are shaped, how targets are addressed, how waits attach, when the batch aborts, and that the result reports what each step did. It omits the 12-step cap and any pacing/rollback note, but nothing here would cause a misinvocation.

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?

The schema documents the sub-properties in detail, and the description adds meaning on top: the per-step object shape, that step arguments mirror the corresponding single-action tool, and the important choice of addressing a target by 'text' rather than 'element' once the screen has changed. 'until' is likewise explained as wait_for semantics plus placement.

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 — run several phone actions in one call — and immediately scopes it with the form-filling example, which makes clear it is a batching wrapper over tap/type/open_app rather than a single action. The action enum and the 'as in that tool' phrasing let an agent tell it apart from the individual step tools in the sibling list.

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?

'when you already know them' is a real selection rule that distinguishes batch use from exploratory step-by-step use with tap/type/read_screen. It also tells the agent to call read_screen after, and that stopped batches surface an approval card. It stops short of naming the individual siblings explicitly as the alternative for single actions.

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