Skip to main content
Glama

Robot Actions — Remote Device Control

by com.robotactions.test
OverviewDiscussionsAdmin

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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Max steps to return (default 200, which is also the ceiling)."New value: +"Max 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."
  2. Added

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations provided, the description carries full burden and does so thoroughly: it discloses output cap/summarisation, failuresOnly returning empty plus a whyNoFailedSteps block, per-step error messages, element locators and find indices, behavior for still-running sessions, and the need to use the same session id for follow-up logs. This goes well beyond what the schema exposes.

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 appropriately so for a debugging tool with subtle behaviors. It is front-loaded with the core purpose and then covers edge cases and follow-up actions in a logical order. Every sentence adds operational value; there is no filler or redundancy that would justify a lower score.

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?

Given there is no output schema and no annotations, the description compensates exceptionally well: it explains output shape highlights, edge cases, progress behavior, and downstream tooling. An agent has enough context to call this correctly, interpret empty results, and know when to escalate to automation_session_step or browser log tools.

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 baseline is 3. The schema already documents sessionId, limit, and failuresOnly, including the 'last n steps' behavior and the ceiling. The description reinforces failuresOnly=true and the idea of requesting filtered views, but adds no genuinely new parameter-level semantics beyond what the schema provides.

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 opens with a specific verb and resource ('Read the step-by-step command history of a run') and immediately frames the tool as the debugging tool, distinguishing it from sibling tools like automation_session_step and session_console_logs. It clearly communicates both what the tool does and how it stands apart.

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 guidance: debugging failed runs, using failuresOnly=true first, checking assertion-failure cases, tracking in-progress runs, and following up with session_console_logs / session_network_logs. It also names the alternative for detailed step inspection (automation_session_step), leaving no ambiguity about workflow.

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
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources