Skip to content

ark_job_capabilities

List the tools ark_job_submit can run in the background, with each one’s input schema.

Only tools enabled by the server configuration and authorized for the caller appear.

Requirement Value
Registration Always registered; no provider credentials required.
Execution Foreground only
Required permission No fixed per-tool scope; HTTP authentication and target-tool authorization still apply.

This site lists the full configured capability surface, not the tools enabled on your particular server. Use model discovery and job discovery to check your connection. Credentials are server configuration, never tool arguments.

Ask your connected AI client to use ark_job_capabilities for the operation you want. The client constructs the arguments and handles tool calls. Review its proposed operation before approving anything billable. For a non-billable introduction, start with discovery without generation.

Call this tool directly. It is not a background-job target.

Exact MCP call (for developers)

The following is an MCP tool-call envelope, not a shell command. Example media URLs and identifiers must be replaced with your own accessible resources. Seedream and Seedance examples are non-billable dry runs; other provider operations may incur charges.

{
"name": "ark_job_capabilities",
"arguments": {}
}

This tool has no input wrapper.

No fields. Pass {}.

Field Type Required Description and constraints
targets array of BackgroundJobTarget No Task-enabled targets available to the current caller.

Field types named above refer to these shared definitions. Optional/null fields, enum choices and bounds are retained in the complete schemas below. Schema validation is followed by runtime capability and security checks.

Input schema, including the MCP wrapper
{
"additionalProperties": false,
"properties": {},
"type": "object"
}
Output schema, including nested definitions
{
"$defs": {
"BackgroundJobTarget": {
"description": "One configured tool that can be submitted as an Ark background job.",
"properties": {
"description": {
"description": "Description of the original target tool.",
"title": "Description",
"type": "string"
},
"input_schema": {
"additionalProperties": {
"$ref": "#/$defs/JsonValue"
},
"description": "JSON Schema for the original target tool arguments.",
"title": "Input Schema",
"type": "object"
},
"required_scope": {
"description": "Tool permission required to submit this target in shared-key HTTP mode.",
"title": "Required Scope",
"type": "string"
},
"task_mode": {
"description": "Native MCP task execution mode for this target.",
"enum": [
"required",
"optional"
],
"title": "Task Mode",
"type": "string"
},
"tool_name": {
"description": "Registered Ark MCP target tool name.",
"title": "Tool Name",
"type": "string"
}
},
"required": [
"tool_name",
"task_mode",
"required_scope",
"description",
"input_schema"
],
"title": "BackgroundJobTarget",
"type": "object"
},
"JsonValue": {}
},
"description": "Configured and authorized background job targets visible to the caller.",
"properties": {
"targets": {
"description": "Task-enabled targets available to the current caller.",
"items": {
"$ref": "#/$defs/BackgroundJobTarget"
},
"title": "Targets",
"type": "array"
}
},
"title": "BackgroundJobCapabilities",
"type": "object"
}
  • Missing tool: check provider credentials and feature flags, then restart the connection.
  • Invalid arguments: keep the correct wrapper and follow current model limits from discovery. A valid schema alone does not prove the chosen model supports the combination.
  • A job completes with an error: inspect the original tool result, not only the outer job status. Never automatically resubmit potentially billable work.
  • Local output writes from jobs require server-configured OUTPUT_ROOTS; HTTP cannot write to a client’s local disk.

See configuration, background execution, and artifact delivery.