Poll a suite run. Returns the run aggregate (status, passed/failed test counts) plus a TestRail-style rollup: per-test status + step counts, an overall summary, and component-step attribution (componentAttributionAvailable is false until the M2 attribution column lands).
| Name | Required | Description | Default |
|---|---|---|---|
| runId | Yes | Run id returned by test_suite_run |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Description discloses that componentAttributionAvailable is false until the M2 attribution column lands, which is useful forward-looking context. However, with no annotations provided, the description carries the full burden for behavioral disclosure. It doesn't state whether this is a read-only operation, whether polling should be throttled, what error conditions exist (e.g., run still in progress), or the shape of the response beyond high-level counts.
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?
One dense sentence, efficiently covers the purpose, output content, and a known limitation. Slightly overloaded with parenthetical detail (componentAttributionAvailable note) but remains under a reasonable length and wastes nothing.
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?
With no output schema, the description should compensate by describing the return value adequately—it lists key output items (run aggregate, per-test status, step counts, overall summary, component attribution). However, given it's a polling tool, the description lacks guidance on what the response looks like while the run is still in progress (does status show 'running', partial counts?), which is important for an agent deciding whether to re-poll.
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% for the single runId parameter. The description adds meaning by clarifying that runId is 'Run id returned by test_suite_run', which ties the parameter to the initiating tool. With only one parameter at full schema coverage, the baseline is met, and the extra linkage adds slight 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 clearly states the tool polls a suite run and returns the run aggregate plus a TestRail-style rollup with per-test status, step counts, an overall summary, and component-step attribution. The verb 'Poll' plus the resource 'suite run' is specific. It distinguishes from siblings like test_suite_run (which starts the run) by the polling orientation, though it doesn't explicitly name siblings.
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 this is the polling counterpart to test_suite_run, which suggests usage for retrieving results after initiating a run. However, it doesn't explicitly state when to use this vs. alternatives like testrail_list_tests_for_run or test_suite_run, nor does it provide clear prerequisites or call cadence (e.g., retry/polling interval 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.
