Find a UI element on an Android device by visible text or content description. Returns element center coordinates in PHYSICAL pixels — use directly with device_tap (no scaling needed).
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | Visible text of the element | |
| udid | Yes | Device serial number (UDID) | |
| resourceId | No | Resource ID of the element (e.g. com.android.chrome:id/url_bar) | |
| contentDesc | No | Content description (accessibility label) of the element |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden. It usefully discloses that the output is in PHYSICAL pixels and requires no scaling — a valuable behavioral detail. However, it doesn't disclose whether the find fails (behavior when no match found), returns first match only, or whether both text and contentDesc can be combined, leaving some behavior opaque.
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, both carrying essential information. The first states the purpose and search criteria; the second imparts the critical coordinate-scaling detail. Zero wasted words.
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 locator tool with 100% schema coverage and a clear integration point (device_tap), the description is largely complete. It explains the core output transformation (physical pixels). It's slightly short on failure behavior and match ambiguity (multiple elements matching the same text), but for this complexity level with full schema coverage it's adequate.
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%, with each of the four parameters (text, udid, resourceId, contentDesc) already described in the schema. The description adds that matches are by 'visible text or content description,' which maps to two params, but doesn't add meaning beyond the schema for resourceId or how parameters interact (e.g., AND vs OR semantics). Baseline 3 is appropriate.
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 verb ('Find') and resource ('UI element on an Android device'), specifies the search criteria (visible text or content description), and differentiates itself from siblings by noting it returns physical pixel coordinates usable directly with device_tap. This distinguishes it from device_tap_by_text, device_locators_for, and device_wait_for_element.
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 this tool (to locate an element before tapping) by explaining the output is directly consumable by device_tap. However, it doesn't explicitly state when NOT to use it or name alternative tools (e.g., device_tap_by_text for direct text-based tapping, device_elements_in_region for region-based queries), which would strengthen usage guidance.
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.
