Measure COLD app-launch time (ms) for a bundle id, averaged over N cold launches. Each run terminates + relaunches the app and times until it is running and idle. Uses the on-device automation agent (auto-started); the agent runner must include the device.perf.launchTime method.
| Name | Required | Description | Default |
|---|---|---|---|
| runs | No | Cold launches to average (default 3) | |
| udid | Yes | iOS device UDID | |
| bundleId | Yes | App bundle id to launch, e.g. com.apple.Preferences |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries full burden of behavioral disclosure. It discloses that each run terminates and relaunches the app (a side effect/destructive behavior), that it uses an on-device automation agent (a dependency), and names a required runner method (device.perf.launchTime). This is good transparency for a measurement tool with no annotation support.
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 three sentences, compact and efficient. It front-loads the core purpose (measure cold launch time) before methodology and dependency details. Every sentence earns its place, though it could be slightly tighter around the methodology clause.
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 benchmarking tool with no output schema and no annotations, the description does a solid job: it states units, what's measured, the averaging semantics, the measurement technique, and the dependency requirement. There is no output schema to document return format, so the description should ideally hint at the return shape (e.g., average ms value), which it doesn't explicitly do, but overall it's well balanced given the tool's moderate complexity.
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% and the description adds meaningful context: it clarifies that runs defaults to 3, and the overall methodology ties all three parameters together (udid, bundleId, runs). The description adds the cold-launch semantics beyond the schema's basic param types.
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 tool measures cold app-launch time in ms for a bundle id, averaged over N cold launches. It names a specific verb+resource+unit (measure COLD launch time), and distinguishes itself from the android_app_launch_time sibling and general device_launch_app tools by the explicit 'COLD' emphasis and averaging behavior.
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 explains the measurement methodology (terminates + relaunches, times until running/idle) which clarifies when this tool is appropriate for launch-time benchmarking vs. the general launch tools. However, it doesn't explicitly contrast against device_launch_app, ios_launch_app, or android_app_launch_time, nor state when NOT to use this tool.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The set contains near-identical duplicate families: web_* and playwright_* expose ~15 pairs of the same desktop-grid-browser operations (web_get_text/playwright_get_text, web_reload/playwright_reload), and screenshot/log/network/mock capabilities each have 5-8 entry points (device_screenshot vs android_mjpeg_screenshot vs ios_screenshot vs ios_fast_screenshot vs web_screenshot vs webpage_screenshot vs session_screenshot). Many individual descriptions carefully draw boundaries (devtools vs traffic, HID vs session), but an agent cannot reliably distinguish web_* from playwright_*, and ios_screenshot/ios_fast_screenshot/ios_mjpeg_screenshot blur together.
The prefix scheme is broken: Android functionality is split arbitrarily between android_* and device_* (device_screenshot vs android_mjpeg_screenshot), the desktop browser gets two parallel prefixes (web_* and playwright_*), and verbs vary across equivalents (device_navigate_url vs web_navigate vs ios_safari_navigate). session_* uses bare verbs (session_url, session_back), and the same concept gets different names (ios_clipboard_get_hid vs ios_get_pasteboard; device_screen vs ios_orientation).
333 tools is an extreme count by any measure — far beyond the 50+ threshold — and much of the bulk is duplicative (the web_*/playwright_* pairs alone double ~15 slots) or out-of-scope for a device-control server (TestRail, Jira, AzDO, agent memory, secret variables, feedback). Even granting that remote device control + test automation is a broad domain, this surface will devastate agent context budgets and is impossible to navigate coherently.
The core device-control and test-automation domain is remarkably thorough: Android and iOS each have full interaction, app-lifecycle, file, network/proxy, performance, crash, accessibility, recording, and replay coverage, with CRUD lifecycles for flows, suites, app uploads, TestRail cases, and visual-review baselines. Minor gaps exist at the margins — Jira/AzDO lack update/transition/comment operations, and iOS cannot open/close tabs — but the central workflows have no dead ends.
