Skip to main content
Glama

View Device recovery browser

device_screenshot_supervisor_task

Retrieve live recovery screenshot pixels for a supervisor job using a job ID and lease token; apply original-to-downscaled width and height scaling for accurate click coordinates.

Instructions

Returns actual live recovery pixels. CLICK uses ORIGINAL screenshot coordinates; apply originalWidth/width and originalHeight/height scaling when downscaled.

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_screenshot_supervisor_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
jobIdYes
leaseTokenYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.5.0

TDQS

C2.3/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden. It does disclose one genuinely useful trait, that clicks must use original, unscaled coordinates, but it omits the lease model implied by jobId/leaseToken (must the job be claimed first? what happens on an expired lease?) and never states the return format (raw image, base64, URL) or whether each call consumes a fresh capture.

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?

Two short sentences with nothing wasted, and the most actionable detail (coordinate scaling) is front-loaded. The terseness itself contributes to the missing information, but as prose it is efficient and well-ordered.

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

Completeness2/5

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

There is no output schema and no annotations, so the description must define the return value and the access model, and it does neither. For a two-required-parameter lease-gated tool, an agent knowing neither what jobId/leaseToken mean nor what comes back cannot reliably invoke it.

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

Parameters1/5

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

Schema description coverage is 0% and the description explains neither parameter. The integer jobId and the 64-character leaseToken are entirely undefined in both places, and the description instead discusses originalWidth/width and originalHeight/height, none of which exist in the input schema, so it adds no usable meaning for the actual arguments.

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

Purpose3/5

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

"Returns actual live recovery pixels" gestures at a screenshot/visual capture operation, but the phrasing is jargon-heavy and never says plainly that it captures a device screenshot. It also gives no signal distinguishing it from the sibling view_check_screenshot, leaving the agent to guess which view tool applies.

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

Usage Guidelines2/5

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

There is no when-to-use guidance, no preconditions, and no named alternative. The agent is told about coordinate scaling but not under what circumstances to call this tool rather than view_check_screenshot or the other supervisor tools.

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