Tool reference · Tasks, workflows & decisions
workflow_track
Records the outcome of one run of a stored workflow and updates its success rate and average duration.
local stdio server writes
When to use
- A workflow run just finished, whether it succeeded or not.
- A run failed and you want the error kept next to the workflow.
- You want workflow_predict to reflect real results over time.
Parameters
| Name | Type | Default | Description |
|---|---|---|---|
workflow_idrequired | string | — | — |
outcomerequired | "success" | "failure" | "partial" | "aborted" | — | — |
duration_ms | integer | — | — |
error_details | string | — | — |
notes | string | — | — |
Example
Arguments
{
"workflow_id": "3f9c2a7e5b1d4c8f9a0e6b2d7c4f1a8e",
"outcome": "failure",
"duration_ms": 185000,
"error_details": "PyPI upload rejected: version already exists",
"notes": "Forgot to bump the version"
}Result shape
{
"run_id": "b71e0c4d92a84f53a6d1e8f07c3b5a29"
}Values are illustrative; the keys follow the server's handler. MCP clients receive the result as JSON text content.
Server description
The description the server sends to your agent in tools/list, captured from the v14.7.0 source:
Record a workflow execution outcome. Outcome ∈ {success|failure|partial|aborted}. Aggregates update automatically.