airflow-mcp-server

airflow-clear-task

Clear and re-run specific task instances in an Airflow DAG run. Optionally include upstream or downstream tasks.

Instructions

Clear specific task instances in an Airflow DAG run (re-run them); supports include_upstream / include_downstream. Write-gated by AIRFLOW_ALLOW_WRITE.

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": {
      "dagId": "<dagId>",
      "dagRunId": "<dagRunId>",
      "taskIds": "<taskIds>"
    },
    "name": "airflow-clear-task"
  }
}

Input Schema

Name	Required	Description
`dagId`	Yes
`dagRunId`	Yes
`taskIds`	Yes	List of task_ids to clear (and re-run)
`includeDownstream`	No
`includeUpstream`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.0.4May 28, 2026
Removedv1.0.2May 15, 2026
First observedv0.1.0May 7, 2026

TDQS

A3.7/5.0

Behavior3/5

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

With no annotations, the description carries the full burden. It mentions that tasks are cleared and re-run, and that writes are gated by an environment variable. However, it does not disclose effects on downstream dependencies, reversibility, or state changes beyond the high-level action. The transparency is adequate but not detailed.

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 description is a single, dense sentence that conveys the core action, key features, and a usage constraint. No unnecessary words or redundancy. Efficiently structured.

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 mutation tool with 5 parameters and no output schema or annotations, the description covers the basic purpose and two important flags. However, it lacks details on return values, prerequisites (e.g., DAG run state), and deeper behavioral context. It is minimally complete but has notable gaps.

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 coverage is low (20%), so the description must clarify parameters. The description explains the boolean parameters (include_upstream/downstream) but does not elaborate on dagId or dagRunId beyond their names. The taskIds parameter already has a schema description. Overall, the description adds some value but leaves some parameter meanings implicit.

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 the action (clear/re-run), the resource (specific task instances in an Airflow DAG run), and the supported flags (include_upstream/downstream). It effectively distinguishes this tool from siblings like airflow-get-task-instances (read-only) and airflow-trigger-dag (new run).

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 description implies usage for re-running tasks but does not explicitly state when to use this tool versus alternatives like triggering a new run or reading task instances. The write gate is mentioned, which provides a usage constraint, but no exclusions or comparative guidance are provided.

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

Deploy Server