Run every test in a suite (and its plans + one level of child suites) SEQUENTIALLY on a device. Returns the run id immediately — the run executes in the background. Poll test_suite_run_status(runId) for progress and the rollup report.
| Name | Required | Description | Default |
|---|---|---|---|
| name | No | Optional label for this run | |
| udid | Yes | UDID of the device to run all resolved tests on | |
| suiteId | Yes | Suite id to execute |
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 key behavioral traits: the run is sequential, includes plans plus one level of child suites, returns immediately (async execution), and executes in the background. It does not explicitly state whether the run is destructive or requires permissions, but for a test execution tool the disclosed traits (async, sequential, background) are the critical behavioral facts.
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, zero wasted words. The first sentence delivers purpose and execution model, the second delivers the async return behavior and the exact follow-up polling tool. Every clause earns its place with no redundant or filler phrasing.
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 test execution tool with 3 parameters, 100% schema coverage, and no output schema, the description is well-rounded. It covers scope (plans + 1 level of child suites), execution model (sequential, background), and follow-up workflow (poll status). The only minor gap is not describing what the runId return value's format looks like, but since the description points to the status polling tool, that's a minor omission.
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 all 3 parameters described in the schema. The description adds context beyond the schema by explaining the runId return value behavior and the poll mechanism, which connects to how parameters flow into status checks. The suiteId and udid are well-explained in schema; the description doesn't duplicate them but adds the operational workflow context.
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 'Run every test in a suite... SEQUENTIALLY on a device' with a specific verb (Run) and resource (test suite). It distinguishes itself from related tools like test_suite_run_status by explaining this tool initiates the run while status must be polled separately. Sibling tools include both test_suite_create and test_suite_run_status, so this description clearly differentiates its role.
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 explicitly says the run executes in the background and instructs to 'Poll test_suite_run_status(runId) for progress and the rollup report.' This provides clear directional guidance (what to call after this tool) and explains the sequential execution model. It names the specific companion tool to use, which is strong 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.
