Accessibility tree of the DESKTOP grid browser page (by pageId), as text — for finding elements and understanding layout. Not a device: the equivalent for a phone or tablet is webpage_snapshot (by udid).
| Name | Required | Description | Default |
|---|---|---|---|
| pageId | Yes | Page ID from web_navigate |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. It discloses that the output is an accessibility tree as text, which is a key behavioral trait, and clarifies it is for the desktop grid browser. It does not mention error conditions or explicitly state read-only behavior, but that is largely implied by the 'snapshot' terminology.
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: the first states what the tool does and its purpose, the second explicitly contrasts with the device alternative. No filler, every sentence adds value.
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?
Given the low complexity—one simple parameter and no output schema—the description fully covers what the tool returns (accessibility tree as text), when to use it, and how it differs from the sibling. It is sufficient for an agent to select and invoke correctly without needing additional context.
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 documents the single parameter (pageId) with a clear description. The tool description adds context by specifying that the pageId refers to a desktop grid browser page, reinforcing the scope defined in the schema. With 100% schema coverage, this is effective.
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 it returns the accessibility tree of the desktop grid browser page as text, with a specific resource (by pageId) and purpose (finding elements, understanding layout). It explicitly distinguishes from webpage_snapshot, making the tool's role unambiguous.
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 direct usage guidance by saying 'Not a device' and then names the exact alternative: 'the equivalent for a phone or tablet is webpage_snapshot (by udid)'. This tells the agent exactly when to use this tool versus a sibling.
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.
