Skip to main content
Glama
saucelabs

Sauce Labs MCP Server

Official
by saucelabs

get_specific_real_device_job_asset

Download device logs, videos, screenshots, or other assets from a real device job using job ID and asset type.

Instructions

    Download a specific asset for a Real Device Cloud (RDC) job.

    USE THIS METHOD WHEN:
    - The job ran on a physical mobile device (iPhone, Android, etc.)
    - get_test_assets returns an error about "Real Device job"
    - get_log_json_file fails with asset not found errors
    - You need logs/videos from mobile app testing

    For web browser testing on virtual machines, use get_test_assets instead.

    :param job_id: Required. The unique identifier of a job running on a real device in the data center. You can look up job
        IDs using the Get Real Device Jobs endpoint.
    :param asset_type: Required. The unique identifier of a job running on a real device in the data center. You can look up job
        IDs using the Get Real Device Jobs endpoint. Possible values are:

        'deviceLogs' - Device Logs | Appium, Espresso, XCUITest
        'appiumLogs' - Appium Logs | Appium
        'appiumRequests' - Appium Requests | Appium
        'junit.xml' - JUnit XML | Espresso, XCUITest
        'xcuitestLogs' - XCUITest Logs | XCUITest
        'video.mp4' - Video | Appium, Espresso, XCUITest
        'screenshots.zip' - Screenshots | Appium, Espresso
        'network.har' - Network Logs | Appium, Espresso, XCUITest
        'insights.json' - Device Vitals | Appium, Espresso, XCUITest
        'crash.json' - Crash Logs | Appium
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
job_idYes
asset_typeYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior3/5

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

No annotations are provided, so the description carries the full burden. It discloses that the tool downloads assets (a read operation), but lacks details about permissions, file size limits, timeouts, or error handling. The behavioral context is adequate but not comprehensive.

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 well-structured with a heading and bullet points, making it scannable. It is reasonably concise for the information provided, though the repeated parameter descriptions could be tightened.

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

Completeness3/5

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

The description mentions that job_id can be looked up using Get Real Device Jobs endpoint, providing some context. However, it does not explain prerequisites, return format, or error cases. Given that an output schema exists, the description's completeness is moderate but not fully self-contained.

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 0%, so the description must compensate. It explains job_id and asset_type, but repeats identical text for both parameters incorrectly for asset_type. It does provide a useful list of possible asset_type values, which adds meaning beyond the schema's bare types. However, the incorrect repetition reduces clarity.

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 clearly states 'Download a specific asset for a Real Device Cloud (RDC) job,' using a specific verb and resource. It distinguishes from siblings like get_test_assets and get_log_json_file by providing use-case guidance, making its purpose unambiguous.

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 provides explicit 'USE THIS METHOD WHEN' conditions, listing three concrete scenarios. It also explicitly states when not to use it ('For web browser testing on virtual machines, use get_test_assets instead'), offering clear alternatives and exclusions.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/saucelabs/sauce-api-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server