Cold app-launch time (ms) via am start -W -S, averaged over N runs. Resolves the launcher activity from the package.
| Name | Required | Description | Default |
|---|---|---|---|
| pkg | Yes | App package (or full component pkg/activity), e.g. com.android.settings | |
| runs | No | Cold launches to average (default 3) | |
| serial | Yes | Android device serial (from `device_list`) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden. It discloses that this measures cold launches specifically (via -S flag which stops the app first), that results are averaged over N runs, and that it resolves launcher activity from package. This is meaningful behavioral context for a read-only measurement tool, though it doesn't note that it terminates the app or describe the exact return format.
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 sentences, zero waste. The first sentence states the measurement and method; the second explains the activity resolution. Every word earns its place and the key purpose is front-loaded.
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 measurement tool with 100% schema coverage and simple parameters, the description is adequately complete. It explains the method, the metric, the averaging behavior, and activity resolution. It could note the output format (ms timestamp/summary) but given the tool's simplicity and full schema coverage, this is a minor gap rather than a blocking one.
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 the schema already documents all three parameters well. The description's mention of 'averaged over N runs' aligns with the `runs` parameter and adds context that runs defaults to 3, which the schema implies but the description confirms. The description doesn't add significant extra semantics beyond the schema's already-good parameter documentation.
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 a specific verb+resource (measure cold app-launch time in ms) with the method used (`am start -W -S`). It also explains it resolves the launcher activity from the package and averages over N runs. This distinguishes it from siblings like device_launch_app (which launches) and ios_app_launch_time (iOS platform).
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 implies when to use it (measuring cold launch performance) but does not explicitly state when NOT to use it or name alternative tools. However, the method detail ('cold' launch, -S flag, averaging runs) provides clear context about the intended use case that distinguishes it from warm-launch or simple launch tools.
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.
