Clear the focused text field on Android by removing its characters: reads the current text length from the UI and sends exactly that many DELETE (backspace) keycodes, after moving the cursor to the end. Tap the field to focus it first. To clear and re-type in one call, use device_type with clearFirst:true instead.
| Name | Required | Description | Default |
|---|---|---|---|
| udid | Yes | Device serial number (UDID) |
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 mechanism (reads text length, sends DELETE keycodes, moves cursor to end) and the requirement to focus the field first. It doesn't describe failure modes or the return value, but for a clear-text operation the disclosed mechanics are reasonably transparent.
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, front-loaded with the purpose, then mechanism, then prerequisite and alternative. Zero wasted words; every sentence earns its place by either stating what it does or how to use it.
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 focused-field clear operation with a single udid parameter and no output schema, the description covers purpose, mechanism, prerequisite (focus), and an alternative approach. It's slightly limited by not describing failure behavior (e.g., what happens if no field is focused), but the core information is complete for an agent to select and invoke 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?
There is only one parameter (udid) at 100% schema coverage, and udid is a standard device serial identifier with no ambiguity. The description focuses on behavior rather than parameters, but with a single self-explanatory required parameter, the schema fully documents it and no additional semantics are needed.
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 clears the focused text field on Android by sending DELETE keycodes equal to the current text length, after moving cursor to end. This is specific (verb=clear, resource=focused text field on Android) and distinguishes from siblings like device_type, ios_clear_text, and device_clear_app_data.
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?
Explicitly states to tap the field to focus it first as a prerequisite. Also names an alternative: 'To clear and re-type in one call, use device_type with clearFirst:true instead.' This provides clear when-to-use guidance and names the sibling alternative directly.
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.
