Force-stop an Android app by package name. Tries the control channel first, falls back to am force-stop, verifies with pidof, and surfaces diagnostic info if the app persists (e.g. Samsung FGS resurrection). Returns { stopped, wasRunning, transport, retryRecommended }.
| Name | Required | Description | Default |
|---|---|---|---|
| udid | Yes | Device serial number (UDID) | |
| packageName | Yes | Android package name to force-stop (e.g. com.android.chrome) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden and delivers richly. It discloses the multi-step behavior (control channel, am force-stop fallback, pidof verification), calls out edge cases (Samsung FGS resurrection), surfaces diagnostic info, and defines the return contract explicitly with the key names. This is excellent behavioral transparency.
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?
Three sentences, front-loaded with the core purpose, followed by mechanism and return value. Efficient and well-structured. Slightly longer than strictly necessary but every clause earns its place, especially the diagnostic edge-case detail and the return schema.
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 2-param tool with no output schema, the description is thorough: it explains the mechanism, verification, failure handling, and return contract. The return keys ({stopped, wasRunning, transport, retryRecommended}) compensate for the missing output schema. One minor gap: it doesn't state what happens when the app isn't running (i.e., stopping a non-running app), but the wasRunning return field partially covers this.
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%, with both parameters (udid, packageName) already described in the schema. The description adds the packageName example context but does not substantially deepen meaning beyond the schema, which already adequately documents both parameters. Baseline 3 is appropriate for full schema coverage.
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 uses a specific verb ('force-stop') plus a resource ('Android app by package name'), clearly distinguishing this from sibling tools like device_launch_app, ios_terminate_app, and device_clear_app_data. It states exactly what the tool achieves and how.
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 its use case (force-stopping a running Android app) but does not explicitly contrast it with alternatives like device_clear_app_data, device_launch_app, or ios_terminate_app. It provides internal fallback strategy details but no when-to-use vs when-not-to-use guidance relative to siblings.
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.
