Skip to main content
Glama
MCP-Airflow-API

MCP-Airflow-API

by call518

pause_dag

Pauses a specified Airflow DAG to prevent scheduling new runs, helping stop unintended executions and control workflow scheduling.

Instructions

[Tool Role]: Pauses the specified Airflow DAG (prevents scheduling new runs).

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": {
      "dag_id": "<dag_id>"
    },
    "name": "pause_dag"
  }
}

Input Schema

NameRequiredDescriptionDefault
dag_idYesExact DAG identifier, as returned by list_dags; not its display name.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.7.4
    • addedInput schema / properties / dag_id / description
      Added value: +"Exact DAG identifier, as returned by list_dags; not its\ndisplay name."
  2. Addedv3.7.2
  3. Removedv3.6.5
  4. Changed2 schema fields changedv3.6.6
    • addedInput schema / additionalProperties
      Added value: +false
    • removedInput schema / properties / dag_id / title
      Removed value: -"Dag Id"
  5. First observed

TDQS

A3.8/5.0
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. The parenthetical 'prevents scheduling new runs' is genuinely valuable because it discloses the scope of the effect — but it stops short of saying whether in-flight runs continue, whether the change is reversible via unpause_dag, or what permissions are required for a mutation.

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?

One sentence with a role tag and a parenthetical that earns its place by adding behavioral meaning. Front-loaded and waste-free.

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?

An output schema exists and the only parameter is fully specified, so the description needn't cover returns. For a simple one-param mutation, the main remaining gap is whether currently running runs are affected — useful but not blocking for correct invocation.

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 100% and the single dag_id parameter is documented in the schema, including the useful 'exact identifier, not display name' note. The description adds nothing beyond that, so the baseline of 3 applies.

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?

States a specific verb (pauses) and resource (the specified Airflow DAG) and immediately clarifies the semantic effect: prevents scheduling new runs. That effect clause cleanly separates it from unpause_dag and trigger_dag, which appear in the sibling list.

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?

Usage is implied by the effect clause rather than stated: an agent can infer 'use when you want to stop new runs from being scheduled.' There is no explicit when-not guidance (e.g., that running task instances are unaffected) and the counterpart unpause_dag is never named.

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