Skip to main content
Glama

Robot Actions — Remote Device Control

by com.robotactions.test

automation_session_commands

Read the step-by-step command history of a run — every action it performed, in order, with duration and pass/fail per step. THIS IS THE DEBUGGING TOOL: to explain why a run failed, fetch it with failuresOnly=true to land directly on the failing step, then read the steps immediately before it for context. When a failed run has NO failed command — an assertion failure, where every WebDriver call succeeded and the test reported the verdict itself — failuresOnly returns no steps and a whyNoFailedSteps block naming what the run reported and which step carried it, so an empty list is never mistaken for "nothing went wrong" and you do not need to re-fetch the whole history to find out. Each entry carries the error message when the step failed, and every element-scoped step (click, sendKeys, getText…) carries the locator that found its element plus the index of the find it came from — so a click at step 24 reads as the button it clicked, not an opaque id. On a run that is still going this returns the steps completed so far, so it is also how you answer "where has it got to?". For browser runs, follow up with session_console_logs / session_network_logs using the SAME session id to see whether a JS error or a failed request explains it. Output is summarised and capped, so ask for a filtered view rather than everything — when a step needs explaining, take its index to automation_session_step for the request/response bodies and the locator behind an element id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax steps to return (default 200, which is also the ceiling). Returns the LAST n steps, not the first — a run that fell over did so at the end. On a long run that means the window can exclude the very failure `firstFailureIndex` points at, so use failuresOnly=true to land on it instead of raising this.
sessionIdYesThe run's session id.
failuresOnlyNoReturn only steps that failed. Use this FIRST when debugging — it is usually one or two rows out of hundreds.

TDQS

A5/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and succeeds: it discloses output summarisation and capping, the whyNoFailedSteps edge case, per-step error messages, locator provenance, behavior on still-running runs, and the fact that limit returns the last n steps. 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.

Conciseness5/5

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

The description is long but every sentence earns its place: it front-loads the core purpose, then covers edge cases, parameter guidance, and sibling routing without redundant filler. Dense, well-ordered, and highly informative rather than bloated.

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 debugging-history tool with no output schema, the description fully covers what the tool returns, how to handle empty results, running runs, follow-up tools, and when to drill into a single step. Nothing an agent needs to correctly select and invoke this tool is missing.

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

Parameters5/5

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

Although schema coverage is 100%, the description adds significant meaning beyond the schema: failuresOnly is described as the first debugging move, limit is explained as returning the last steps rather than the first, and its interaction with firstFailureIndex and failuresOnly is called out. The description meaningfully augments the parameter definitions.

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 first sentence names a specific verb and resource: 'Read the step-by-step command history of a run — every action it performed, in order, with duration and pass/fail per step.' It clearly differentiates from nearby siblings by declaring itself 'THE DEBUGGING TOOL' and pointing to automation_session_get and automation_session_step for adjacent concerns.

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

Usage Guidelines5/5

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

The description gives explicit when-to-use instructions: use failuresOnly=true first when debugging, explains the assertion-failure case, and states when to follow up with session_console_logs / session_network_logs. It also directs when to escalate to automation_session_step for deeper detail, so the agent gets concrete routing among alternatives.

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