grr

Overview Schema Source Related Servers Discussions Admin

analyticsdata.properties.audienceExports.create

Creates an audience export snapshot of users for a property and returns its resource name, so you can retrieve the user list later with the query method.

Instructions

Creates an audience export for later retrieval. This method quickly returns the audience export's resource name and initiates a long running asynchronous request to form an audience export. To export the users in an audience export, first create the audience export through this method and then send the audience resource name to the QueryAudienceExport method. See Creating an Audience Export for an introduction to Audience Exports with examples. An audience export is a snapshot of the users currently i [HTTP POST] — creates or triggers a change; refused under --readonly safety profiles. Returns the API's response resource as JSON — request body is a JSON AudienceExport object accepting audience, audienceDisplayName, beginCreatingTime, creationQuotaTokensCharged, dimensions, errorMessage, name, percentageCompleted and 2 more fields; pass it via params or whole via body_file Siblings over the same resource: get, list, query.

Input Schema

Name	Required	Description
`query`	No	Extra KEY=VALUE query pairs for endpoints whose parameters Discovery does not describe.
`params`	No	Parameter map merged into the request; typed parameters win.
`parent`	Yes	[URL path segment] Required. The parent resource where this audience export will be created. Format: `properties/{property}`
`dry_run`	No	Return the request that would be sent, without sending it.
`body_file`	No	Read the request body from this file ('-' for stdin) instead of building one from the parameters. The body is a JSON AudienceExport object.
`request_body`	No	Request body of type AudienceExport: pass it via `params` (merged into the built body) or whole via `body_file`.

Output Schema

Name	Required	Description	Default
`done`	No
`name`	No
`error`	No
`metadata`	No
`response`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 26, 2026

changedInput schema / properties / body_file / description

Previous value: -"Read the request body from this file ('-' for stdin) instead of building one from the parameters."New value: +"Read the request body from this file ('-' for stdin) instead of building one from the parameters. The body is a JSON AudienceExport object."

addedInput schema / properties / request_body

Added value: +{
+  "description": "Request body of type AudienceExport: pass it via `params` (merged into the built body) or whole via `body_file`.",
+  "properties": {
+    "audience": {
+      "type": "string"
+    },
+    "audienceDisplayName": {
+      "type": "string"
+    },
+    "beginCreatingTime": {
+      "type": "string"
+    },
+    "creationQuotaTokensCharged": {
+      "type": "integer"
+    },
+    "dimensions": {
+      "items": {
+        "properties": {
+          "dimensionName": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "errorMessage": {
+      "type": "string"
+    },
+    "name": {
+      "type": "string"
+    },
+    "percentageCompleted": {
+      "type": "number"
+    },
+    "rowCount": {
+      "type": "integer"
+    },
+    "state": {
+      "enum": [
+        "STATE_UNSPECIFIED",
+        "CREATING",
+        "ACTIVE",
+        "FAILED"
+      ],
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Changed3 schema fields changedOct 26, 2026

changedInput schema / properties / parent / description

Previous value: -"Required. The parent resource where this audience export will be created. Format: `properties/{property}`"New value: +"[URL path segment] Required. The parent resource where this audience export will be created. Format: `properties/{property}`"

addedInput schema / properties / parent / pattern
```
Added value: +"^properties/[^/]+$"
```

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "done": {
+      "type": "boolean"
+    },
+    "error": {
+      "properties": {
+        "code": {
+          "type": "integer"
+        },
+        "details": {
+          "items": {
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "message": {
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "metadata": {
+      "type": "object"
+    },
+    "name": {
+      "type": "string"
+    },
+    "response": {
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

First observedOct 26, 2026

TDQS

A4/5.0

Behavior4/5

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

No annotations are supplied, so the description carries the full load and does well: it discloses the async long-running behavior, that the call returns immediately with a resource name, the HTTP POST/readonly-profile refusal, and the request body shape. It omits quota/cost implications and what a partial or failed export looks like beyond the errorMessage field name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The workflow guidance is front-loaded and useful, but the text is padded with a redundant enumeration of request-body fields ('...and 2 more fields') that the schema already covers, and it contains a truncated fragment ('a snapshot of the users currently i') that reads as broken text.

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?

For an async mutation with a nested body and an output schema present, the description supplies the essential mental model: create returns a name, then query to read results. Return-value details are rightly left to the output schema, and the broken snapshot sentence is the main remaining gap.

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 description coverage is 100% and the required `parent` format is fully documented there. The description's field list (audience, dimensions, percentageCompleted, etc.) merely repeats what the schema already enumerates, and the 'via `params` or `body_file`' note duplicates the schema's own descriptions, so it adds no semantics beyond the structured data.

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 and resource ('Creates an audience export') and immediately explains the two-phase nature: a quick resource-name return plus a long-running async job. The closing line names the siblings over the same resource (get, list, query), so it is distinguishable from them without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives an explicit workflow: call this first, then pass the audience resource name to `QueryAudienceExport` to retrieve the users. That is real routing guidance, though it does not say when to prefer this over the sibling list/get calls or what to do if an export already exists.

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

Deploy Server