ui_automate

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

Annotations already mark this as destructive, non-read-only, and non-open-world. The description adds meaningful behavior beyond them: UIKit control/accessibility actions rather than touch injection, no implicit waits/screenshots/text, after_capture reuse, first-failure stopping, and no automatic retry of mutations. It does not state what state can be destroyed or any auth/precondition requirements, keeping it below 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?

The description is compact and front-loaded: it opens with the core batch operation and then layers in mechanism, targeting, and failure semantics. Each sentence adds a constraint or capability, with no filler.

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 14-parameter automation tool with no schema descriptions, the description covers the main runtime model but not enough of the parameter surface to call it confidently without inspecting the schema. Output schema handles return values and annotations cover safety, but the missing parameter guidance leaves the definition incomplete.

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?

With 0% schema description coverage across 14 parameters, the description must carry parameter meaning. It explains target selection (leased view_id, identifier/class/text, window x+y) and mentions after_capture, but leaves required device_id/bundle_id, the steps array, and most tuning/capture parameters (depth, limit, fields, format, max_nodes, settle_ms, include_text, root_view_id, visible_only, controls_only) unexplained.

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 names a specific verb and resource: 'Run an app-scoped batch,' then enumerates the supported steps (tap, back/dismiss, input_text, scroll, assert, wait_for). It also clarifies the mechanism is UIKit control/accessibility actions rather than physical touch injection, though it does not explicitly name sibling tools like ui_snapshot or ui_capture as alternatives.

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?

It implies the tool is for app-scoped UI action batches and gives operational constraints (stops on first failure, no automatic retry, no implicit wait/screenshots/text, optional after_capture). However, it never states an explicit 'use this when' rule or names when to prefer a sibling tool such as ui_capture for screenshots, so guidance remains implied.

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