Skip to main content
Glama
dolphin-mcp-pilot

dolphin-mcp-pilot

ds_run_workflow

Trigger a DolphinScheduler workflow run, bring it online first, and optionally start from selected tasks with alert configuration.

Instructions

Manually trigger a workflow run (brings it online first).

Args: project_name: Project name workflow_code: Process-definition code start_task_names: Optional list of task names to start from (including their downstream tasks). Leave empty to run the entire workflow. Example: ["partition_check"] starts from that task and all its successors. warning_type: NONE, SUCCESS, FAILURE (default) or ALL warning_group_id: Alert group ID; positive when alerts are enabled

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": {
      "project_name": "<project_name>",
      "workflow_code": "<workflow_code>"
    },
    "name": "ds_run_workflow"
  }
}

Input Schema

NameRequiredDescriptionDefault
project_nameYes
warning_typeNoFAILURE
workflow_codeYes
start_task_namesNo
warning_group_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.6/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden, and it does contribute one important non-schema fact: the workflow is brought online as part of the run, which is a real side effect on definition state. It also explains the alerting knobs. What is missing is whether the call blocks until completion or returns immediately, what identifier it returns (there is no output schema), and what permissions or role the caller needs for a state-changing operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The purpose sentence is front-loaded and the parameter list follows in a scannable docstring format with no filler. Every line either disambiguates an ambiguous field or supplies an enum/example the schema lacks.

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?

For a five-parameter mutation tool with no annotations and no output schema, most of what an agent needs is present, especially the run-scope semantics of start_task_names. The definition still leaves the caller blind about the result of the call and about execution mode (synchronous vs fire-and-forget), which matters for a trigger tool.

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

Parameters4/5

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

Schema description coverage is 0%, so the description must carry parameter meaning, and it largely does: it supplies the enum values for warning_type (NONE, SUCCESS, FAILURE/ALL) that the schema omits, explains that start_task_names includes downstream tasks and that empty means the whole workflow, and notes warning_group_id is positive when alerts are enabled. The weak spot is minor redundancy ('Project name', 'Workflow Code') and the vague 'Process-definition code' phrasing when the schema types it as an integer.

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

Purpose4/5

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

States a specific verb and resource: 'Manually trigger a workflow run', with the qualifier 'Manually' distinguishing it from scheduled execution and '(brings it online first)' marking it as a state-changing action rather than a read. It does not explicitly contrast itself with siblings such as ds_release_workflow or ds_create_workflow, so an agent must infer which workflow-lifecycle 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 Guidelines3/5

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

The word 'Manually' implies on-demand use versus scheduling, and the start_task_names section gives genuine operational guidance ('Leave empty to run the entire workflow', with a concrete example of starting mid-graph). However, there is no statement of prerequisites, no note on what happens if a run is already in progress, and no explicit alternative tool to use when you want to schedule rather than trigger.

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