Skip to main content
Glama
IBM

IBM watsonx.data MCP Server

Official
by IBM

submit_spark_application

Submit a Spark application to a specified engine for execution, with configurable arguments, properties, and environment variables.

Instructions

Submit a Spark application for execution on a Spark engine.

Args: engine_id: Spark engine identifier application: Application file path (JAR, Python, R file) arguments: Application arguments array conf: Spark configuration properties (e.g., {"spark.executor.memory": "2g"}) env: Environment variables name: Application name (will be added to conf as spark.app.name) job_endpoint: External job endpoint service_instance_id: Service instance ID - "iae" or "emr" type: Engine type - "spark" or "gluten" context_type: Context type - "project", "git_project", or "space" volumes: Volume mounts (watsonx.data software only). List of dicts with: - name: volume name - mount_path: path in spark cluster (e.g., "/mount/path") - source_sub_path: path in volume to mount (e.g., "/source/path") - read_only: boolean flag

Returns: Dict with application_id, state, and submission details

Examples: Minimal configuration for IBM Cloud Object Storage using cos:// protocol:

{
  "engine_id": "spark398",
  "application": "cos://bucket.instance/app.py",
  "arguments": ["cos://bucket.instance/data.csv"],
  "conf": {
    "spark.hadoop.fs.cos.instance.endpoint": "s3.direct.us-east.cloud-object-storage.appdomain.cloud",
    "spark.hadoop.fs.cos.instance.access.key": "your-access-key",
    "spark.hadoop.fs.cos.instance.secret.key": "your-secret-key"
  }
}

Minimal configuration for IBM Cloud Object Storage using s3a:// protocol:

{
  "engine_id": "spark398",
  "application": "s3a://bucket/app.py",
  "arguments": ["s3a://bucket/data.csv"],
  "conf": {
    "spark.hadoop.fs.s3a.bucket.bucket.access.key": "your-access-key",
    "spark.hadoop.fs.s3a.bucket.bucket.secret.key": "your-secret-key",
    "spark.hadoop.fs.s3a.bucket.bucket.aws.credentials.provider": "org.apache.hadoop.fs.s3a.SimpleAWSCredentialsProvider"
  }
}

Optional conf parameters (uses engine defaults if not specified):
- spark.app.name: Custom application name
- ae.spark.driver.log.level / ae.spark.executor.log.level: Log levels
- spark.driver.cores / spark.driver.memory: Driver resources
- spark.executor.cores / spark.executor.memory: Executor resources

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
engine_idYes
applicationYes
argumentsNo
confNo
envNo
nameNo
job_endpointNo
service_instance_idNo
typeNo
context_typeNo
volumesNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Behavior2/5

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

No annotations provided. Description does not disclose side effects, blocking behavior, authentication requirements beyond examples, or rate limits. Lacks disclosure of potential errors.

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?

Well-structured with Args, Returns, Examples, and Optional params sections. Slightly verbose but justified by complexity of the tool.

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?

Covers all 11 parameters, provides return type, and includes examples. Lacks error handling or state change details, but adequate for typical use.

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

Parameters5/5

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

With 0% schema description coverage, the description excellently explains each parameter's purpose and format, including examples for conf, volumes structure, and name auto-injection into conf.

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?

Clear verb+resource: 'Submit a Spark application for execution on a Spark engine.' Distinguishes from sibling tools like get_spark_application_status or stop_spark_application.

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

Usage Guidelines3/5

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

Provides examples for common configurations (COS, S3A) but does not explicitly state when to use this tool versus alternatives or prerequisites. No when-not-to-use guidance.

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/IBM/ibm-watsonxdata-mcp-server'

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