Minds: Synthetic Market Research

Duplicate Audience

duplicate_audience

Adds an independent copy of an Audience, its Minds and retained knowledge. Unready copies can queue retraining with public web research when retained evidence cannot seed them. Ready copies avoid retraining.

Input Schema

Name	Required	Description
`name`	No	Name of the copy. Defaults to "<name> (copy)".
`audienceId`	Yes	Audience to duplicate; you must be able to edit it. The copy is private and gets new Minds (profiles, knowledge, embeddings) plus the grounding, sources, formations and finished validations; it counts against the Mind allowance. While the Audience is still being built the copy is its last good state; copied members without a working version are retrained on their own.
`idempotencyKey`	No	Retry key. Without one, an identical call within 15 minutes returns the same copy instead of a second one; send a new key only to deliberately make another copy of the same source with the same name.

Output Schema

Name	Required	Description
`data`	No	The new Audience: id, name, mindCount, mindIds, minds and sharing state (always private).
`audienceUrl`	No	Minds workspace link for the new Audience.
`idempotencyKey`	No	Key of this duplication; reuse it to retry without creating a second copy.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 11, 2026

changedInput schema / properties / audienceId / description

Previous value: -"Audience to duplicate; you must be able to edit it. The copy is private and gets new Minds (profiles, knowledge, embeddings) plus the grounding, sources, formations and finished validations; it counts against the Mind allowance. Refused while the Audience is still being built."New value: +"Audience to duplicate; you must be able to edit it. The copy is private and gets new Minds (profiles, knowledge, embeddings) plus the grounding, sources, formations and finished validations; it counts against the Mind allowance. While the Audience is still being built the copy is its last good state; copied members without a working version are retrained on their own."

Changed1 schema field changedOct 6, 2026

changedInput schema / properties / idempotencyKey / description

Previous value: -"Retry key. Reuse the key a failed or timed-out call returned so the retry cannot create a second copy."New value: +"Retry key. Without one, an identical call within 15 minutes returns the same copy instead of a second one; send a new key only to deliberately make another copy of the same source with the same name."

Changed4 schema fields changedOct 2, 2026

removedOutput schema / properties / audienceUrl / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / audienceUrl / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / idempotencyKey / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / idempotencyKey / type
```
Added value: +[
+  "string",
+  "null"
+]
```

AddedSep 30, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already flag a non-read-only, open-world, non-idempotent but non-destructive write. The description adds real value beyond that: it discloses that copying can trigger retraining with public web research, that ready copies skip retraining, and that the copy is independent. Permissions (must be able to edit) and allowance impact are left to the schema, which is a minor gap for a write tool.

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

Conciseness4/5

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

Three sentences, front-loaded with the action and scope, then the two conditional behaviors. Dense but every sentence carries behavioral information; only the unqualified jargon ("Minds", "formations", "retained evidence") slightly reduces first-read clarity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool's complexity is modest (one required param, an output schema, and annotations covering safety and open-world behavior), and the description fills the remaining gap by explaining what gets copied and when retraining occurs. An agent has enough to call it correctly without asking a follow-up.

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%, so audienceId, name, and idempotencyKey are already fully documented, including defaults and retry semantics. The description adds no parameter-level meaning beyond what the schema provides, which is the baseline-3 case when the schema does the heavy lifting.

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 ("Adds an independent copy of an Audience") and enumerates exactly what is copied (its Minds and retained knowledge), so the agent knows the scope of the operation without opening the schema. The Audience resource is unambiguous against the study-oriented siblings such as duplicate_study.

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?

The description describes outcomes for two states (unready copies queue retraining; ready copies avoid retraining) but never states when an agent should choose this tool, nor points to an alternative such as create_audience_from_brief. Usage is only implied by the act of duplicating.

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

All Minds: Synthetic Market Research tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.