Launch an Android app. Accepts a package name (e.g. com.android.chrome) OR a display name (e.g. "Chrome"). Display-name lookup is case-insensitive substring match against installed apps.
| Name | Required | Description | Default |
|---|---|---|---|
| udid | Yes | Device serial number (UDID) | |
| packageName | Yes | Package name (com.x.y) OR display name (case-insensitive substring) |
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 the case-insensitive substring matching behavior for display names, which is genuinely useful. However, it doesn't mention what happens on failure (app not found, invalid package), side effects, or whether a launch while already running brings to foreground vs restarts. For a launch tool with zero annotations, this is adequate but not rich.
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 concise sentences with concrete examples (com.android.chrome, 'Chrome'). Front-loaded with the core verb and object. The example package names add practical clarity. Uses as the term 'OR' and effectively front-loads the important dual-input capability.
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 launch tool with only 2 simple parameters, 100% schema coverage, and no output schema, the description covers the essential decision points: what it does, accepted input forms, and matching behavior. It could mention failure states but overall provides sufficient context for an agent to invoke it correctly.
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 already covers both parameters at 100%, and the description adds meaningful detail beyond the schema: it elaborates that packageName can be either a package name or display name, and defines the substring/case-insensitive matching semantics. This adds clear value over the bare schema text, which only says 'Package name (com.x.y) OR display name (case-insensitive substring)' — the description reinforces and expands this.
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 launches an Android app, with a specific verb + resource combination. It adds useful detail about accepting either a package name OR display name, and explains the matching semantic (case-insensitive substring). It doesn't explicitly differentiate from siblings like device_launch_app_in_language or ios_launch_app, but the Android scope and dual-name capability are clear.
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 clarifies the two acceptable input forms (package name vs display name) and describes the lookup behavior. It does not explicitly state when to use this vs device_launch_app_in_language or device_navigate_url, but the Android-specific naming and the launch-focused purpose give reasonable implicit context. No explicit exclusions or alternatives are named.
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.
