Skip to main content
Glama

device_start supervisor task

device_start_supervisor_task

Start or resume an isolated device recovery browser at the task URL to resolve incidents, then capture screenshots and perform visible challenge actions while the user handles login/2FA.

Instructions

Start an isolated Device recovery browser at the task URL using its current proxy, or resume the incident session. Requires allowDeviceSessions. Consumes one repair attempt. sourceId is required for Intelligence. Use device_status for a screenshot and device_command for visible challenge clicks or saving; hand login/2FA to the user. Requires a write-scope key.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "jobId": "<jobId>",
      "leaseToken": "<leaseToken>"
    },
    "name": "device_start_supervisor_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdYes
sourceIdNo
leaseTokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full load and does disclose the costly side effect ("Consumes one repair attempt"), the authorization gates (allowDeviceSessions, write-scope key), and the isolation/proxy model. It does not state what is returned or what happens if the attempt fails, leaving a gap for a state-mutating tool.

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?

Front-loaded with the action and mode, then constraints in short clauses; nearly every sentence adds a decision-relevant fact. The two separate "Requires ..." fragments could be merged, but nothing is padding.

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

Completeness4/5

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

For a mutation tool with no annotations and no output schema, the description covers authorization, cost, alternatives, and human-handoff boundaries well. The remaining gap is parameter meaning and error/return behavior, which is meaningful but secondary.

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

Parameters2/5

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

Schema description coverage is 0% for three parameters, so the description must compensate. It only adds meaning for sourceId ("required for Intelligence"); jobId and leaseToken are never explained, nor is the 64-char lease token's role or origin.

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?

States a specific verb ("Start") plus a precisely scoped resource ("isolated Device recovery browser at the task URL using its current proxy") and an alternate mode ("resume the incident session"). It explicitly differentiates itself from siblings by naming device_status and device_command for adjacent actions.

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?

Gives explicit routing: use device_status for screenshots, device_command for visible challenge clicks or saving, and hand login/2FA to the user. It also names prerequisites (allowDeviceSessions, write-scope key, sourceId for Intelligence), so an agent can decide before calling whether it is eligible.

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