Long press at (x,y) on an Android device screen. Triggers context menus, drag handles, and other long-press actions. Coordinates are PHYSICAL pixels (from page_source bounds).
| Name | Required | Description | Default |
|---|---|---|---|
| x | Yes | X coordinate in physical pixels (from page_source bounds) | |
| y | Yes | Y coordinate in physical pixels (from page_source bounds) | |
| udid | Yes | Device serial number (UDID) | |
| duration | No | Hold duration in ms (default: 800) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries some behavioral burden. It communicates the coordinate convention (physical pixels from page_source bounds) which is genuinely useful. However, it doesn't disclose behavior like whether the hold is exact or approximate, whether the duration default matters for triggering certain menus, or any side effects/state changes.
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?
The description is two sentences with no fluff. It front-loads the core action and adds the important coordinate-system caveat. Every sentence earns its place without redundancy.
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 simple interaction tool with 100% schema coverage and no output schema needed (post-action effects are the output), the description covers the essential context: what it does, coordinate convention, and typical use cases. Slight room for improvement on edge-case behavior, but it's largely complete for this tool class.
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 input schema documents all four parameters (x, y, udid, duration with default 800ms). The description adds the note about physical pixels, which reinforces the schema. This is the baseline 3 case: schema does the heavy lifting with some minor reinforcement from the description.
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 'Long press at (x,y) on an Android device screen' with a specific verb, resource, and coordinate scope. It distinguishes this from sibling tools by naming the action type, and it explicitly mentions the coordinate system (PHYSICAL pixels) which adds critical scoping detail.
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 gives some usage context by listing what long-press actions typically trigger ('context menus, drag handles'). However, there's no explicit when-to-use vs alternatives guidance, no exclusions, and no comparison with related tools like device_tap or device_drag_drop, though the purpose difference is largely self-evident.
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.
