Press a key in the DESKTOP grid browser (by pageId) — Enter, Tab, Escape, ArrowDown, or a chord like Control+A. Targets an element when a selector is given, otherwise the focused one. Not a device — for a phone or tablet use webpage_press_key.
| Name | Required | Description | Default |
|---|---|---|---|
| key | Yes | Key name, e.g. Enter / Tab / Escape / ArrowDown / Control+A | |
| pageId | Yes | Page ID from web_navigate | |
| selector | No | CSS selector to focus first; omit to use focus as-is |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the behavioral burden. It explains how target selection works ('Targets an element when a selector is given, otherwise the focused one') and discloses the platform boundary. It could mention potential side effects like form submission or navigation, but the core behavior is 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 with no filler: the first establishes action, context, and key syntax; the second clarifies targeting behavior and routes to the mobile alternative. Everything earns its place.
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 3-parameter action with fully described schema, the description and schema together cover what the tool does, where it runs, how target selection works, and where to send phone/tablet requests. No output schema exists, so explaining return values is unnecessary.
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%, and the schema already describes pageId, key examples, and selector behavior. The description's key examples and selector-targeting note largely mirror the schema text ('CSS selector to focus first; omit to use focus as-is'), adding little new semantic value.
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 opens with a concrete action and resource: 'Press a key in the DESKTOP grid browser (by pageId)' followed by concrete key examples. It also explicitly distinguishes the tool from webpage_press_key, so an agent can tell them apart from a large sibling list.
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?
It gives a clear usage context ('DESKTOP grid browser') and an explicit when-not/alternative: 'Not a device — for a phone or tablet use webpage_press_key.' This directly routes the agent to the correct sibling tool for a different platform.
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.
