Skip to main content
Glama

Robot Actions — Remote Device Control

by com.robotactions.test

automation_session_step

Open ONE step of a run in full: its request body, its response body, status, timing, and — for element-scoped steps — the locator that actually found the element. Use automation_session_commands first to get the step index, then come here for the step that matters. THIS IS HOW YOU ANSWER "which element?": a click/sendKeys/getText step addresses its element by an opaque id in the URL and arrives with an empty body, so the step alone never names what it touched; this resolves that id back to the findElement that produced it and returns the using/value locator. networkDuring lists the page requests that overlapped the step, so a click that failed while an XHR was in flight is visible as such — browser runs only, and it says so explicitly when the run captured no network traffic rather than returning an empty list that reads as "nothing happened".

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
indexYesWhich step, as the `index` reported by automation_session_commands. Indexes are positions in the FULL history, so they stay valid regardless of any window that tool applied.
sessionIdYesThe run's session id.
includeNetworkNoCorrelate page network traffic to this step (default true). Set false to skip the extra lookup.

TDQS

A4.4/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden, and it delivers: it reveals that element-scoped steps reference an opaque id with an empty body, that networkDuring is browser-only, and that a no-traffic run returns an explicit 'no network captured' signal rather than an empty list that could be misread. This is unusually rich behavioral disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense and somewhat long, but nearly every sentence adds operational value: workflow, locator resolution, and networkDuring edge-case behavior. The emphatic 'THIS IS HOW YOU ANSWER' phrasing is stylistically noisy, but it flags the tool's most important diagnostic use case.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with no output schema and no annotations, the description covers the main return values, the required predecessor tool, the special locator-resolution behavior, and an important edge case (no network captured). An agent has enough context to call and correctly interpret the result.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents sessionId, index, and includeNetwork. The description reinforces the index semantics by pointing to automation_session_commands and explains the networkDuring output behavior, but it doesn't need to add additional parameter-level detail.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and resource ('Open ONE step of a run in full') and enumerates what is returned: request body, response body, status, timing, and locator for element-scoped steps. It explicitly contrasts with automation_session_commands, so an agent can distinguish the two tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It provides explicit sequencing: 'Use automation_session_commands first to get the step index, then come here for the step that matters.' It also identifies the special case where this tool is required to answer 'which element?', giving condition-based routing. It doesn't enumerate exclusions, but the guidance is clear enough for correct selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Robot Actions — Remote Device Control toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0
Disambiguation2/5

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.

Naming Consistency2/5

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).

Tool Count1/5

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.

Completeness4/5

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.

Resources