> ## Documentation Index
> Fetch the complete documentation index at: https://docs.agentlinkops.com/llms.txt
> Use this file to discover all available pages before exploring further.

# Get placement classification job

> Read a saved classification job.

`get_placement_classification_job`

Read a saved classification job. Reading neither dispatches nor retries provider work. Suggested labels and reviewed decisions remain independent of link presence and index status.

<Note>Development preview. This command is absent from the verified deployed bundle. Use a matching development environment.</Note>

| Access | Behavior |
| - | - |
| `watches:read` | Reads saved data |

This read does not start a verification job.

## Example request

Connect through [MCP](/guides/connect-mcp), [CLI](/guides/connect-cli), or [HTTP](/guides/connect-http). Replace example identifiers with records from your workspace.

<CodeGroup>
  ```json MCP theme={null}
  {
    "jsonrpc": "2.0",
    "id": 1,
    "method": "tools/call",
    "params": {
      "name": "get_placement_classification_job",
      "arguments": {
        "watchId": "watch_example",
        "jobId": "classification_job_example"
      }
    }
  }
  ```

  ```bash CLI theme={null}
  agentlinkops call get_placement_classification_job --args '{"watchId":"watch_example","jobId":"classification_job_example"}'
  ```

  ```bash HTTP theme={null}
  curl "$AGENTLINKOPS_API_URL/v1/commands/get_placement_classification_job" \
    -H "Authorization: Bearer $AGENTLINKOPS_API_KEY" \
    -H 'Content-Type: application/json' \
    --data '{"watchId":"watch_example","jobId":"classification_job_example"}'
  ```
</CodeGroup>

## Returned result

Illustrative data validated against the documented response schema. IDs and dates are examples, not a live account capture. MCP returns this data in `structuredContent` and in a text content block; generic HTTP and CLI return the JSON result directly.

```json theme={null}
{
  "id": "classification_job_example",
  "state": "succeeded",
  "reason": null,
  "canReconcile": false
}
```

## Input fields

Omit optional fields when you do not want to supply them. Null is accepted only where listed. Unknown input properties are rejected.

| Field | Type | Presence | Meaning and constraints |
| - | - | - | - |
| `watchId` | string | Required | Identifier of the watch returned by its create or list operation. minLength: 1; maxLength: 200 |
| `jobId` | string | Required | Identifier of the job returned by its create or list operation. minLength: 1; maxLength: 200 |

### Validation and omitted values

Reads the existing job without repairing or retrying it. A reconciliation\_required state never authorizes a provider retry. When canReconcile is true, a retained result and its original settled usage receipt support explicit publication recovery, subject to current evidence and access checks.

Link presence, Google index evidence, source authority and customer acquisition records remain independent of classification.

Current retained evidence, project access and the classification revision govern writes. An expired or changed source cannot authorize a current label. Existing keys and grants do not silently gain classification:write.

## Output fields

Fields inside optional or nullable parents apply only when that parent exists. [Common schema conventions](/reference/schemas) explain evidence states, empty lists and extensions.

| Field | Type | Presence | Meaning and constraints |
| - | - | - | - |
| `id` | string | Required | Resource identifier returned by the operation. minLength: 1; maxLength: 200 |
| `state` | string | Required | Saved lifecycle or evidence state, as enumerated for this record. values: "queued", "dispatched", "succeeded", "failed", "reconciliation\_required", "cancelled" |
| `reason` | string / null | Optional | Recorded explanation; null when no explanation applies. |

[Download input schema](/schemas/get_placement_classification_job.input.json) · [Download output schema](/schemas/get_placement_classification_job.output.json)

## Errors and retries

The command is annotated idempotent. Reuse an accepted idempotency key when the input provides one; changing the payload under a reused key can conflict. Operation-specific errors include `CLASSIFICATION_PRECONDITION_CHANGED`, `CLASSIFICATION_EVIDENCE_EXPIRED`, `CLASSIFICATION_ACCESS_DENIED`.

See [error recovery](/reference/errors) for status, scope, cooldown, cursor and retry handling. Unknown observations are result data and do not establish loss.

## HTTP resource routes

These existing resource routes share the operation’s domain behavior. Their parameter placement, status and response envelope can differ from generic invocation. See [HTTP route details](/reference/http/routes).

| Method and route | Success | Details |
| - | - | - |
| `GET /v1/watches/{watchId}/classification/jobs/{jobId}` | 200 | Reads the existing job without repairing or retrying it. A reconciliation\_required state never authorizes a provider retry. When canReconcile is true, a retained result and its original settled usage receipt support explicit publication recovery, subject to current evidence and access checks. |

## Continue

[get\_placement\_context](/reference/commands/get_placement_context)

Follow the [related workflow](/guides/monitor-changes), inspect [capability status](/capability-status), or return to the [command index](/reference/index).


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.