WdsRetrieve
Searches retrieval-indexed crawled content in the default MCP tenant to find evidence relevant to a question, optionally restricted to one named job
Arguments
| Name | Type | Required | Default | Description |
|---|---|---|---|---|
| query | string | Yes | None | Search query used to find relevant indexed content chunks |
| jobName | string? | No | null |
Optional. Exact job name in the default MCP tenant. When provided, searches only content indexed for that job and requires the job to exist; omit or pass null to search indexed content across all jobs |
| threshold | string? | No | null |
Optional. Retrieval score threshold. Use an invariant-culture float from 0 to 1 or one of: exact-match, same-category, same-domain, generic-similarity. Omitted, null, or unrecognized text uses same-domain |
| limit | int? | No | null |
Optional. Maximum number of retrieval results to return. Omitted or null uses 10 |
Return Type
Returns RetrievalItem[].
Technical return shape: array of RetrievalItem.
Structured Output
The MCP structured result is an object whose result property contains the RetrievalItem[] value.
Data Contracts
RetrievalItem
One matched indexed content chunk returned by retrieval
Fields:
| Name | Type | Description |
|---|---|---|
| Score | float | Relevance score for this retrieval match; higher values are returned first |
| Span | string | Matched text span with semantic context |
| DownloadTasks | array of DownloadTaskInfo | Downloaded pages that contain the matched text |
DownloadTaskInfo
Source download task for a retrieval match
Fields:
| Name | Type | Description |
|---|---|---|
| DownloadTaskId | string | Download task ID |
| Url | string | Source page URL |
| CaptureDateUtc | datetime | Date and time when the source page was captured, in UTC |
Behavior
Read-only: yes; idempotent: yes; destructive: no; open-world: no.
Availability
Requires the Retrieval feature.