Minds: Synthetic Market Research

Create a Study

create_study

Idempotent

Creates a Study workspace from existing Audiences or inline Audience configurations. It does not ask questions or run research, and follow-up research inside an existing Study needs no new Study.

This always creates: a matching name never attaches to an existing Study, and only a byte-identical repeat of the same call replays the Study the first one made, reported as replayed: true. Settle the Audience set before calling — nothing adds an Audience to an existing Study afterwards, and Studies cannot be deleted here, so calling again with one extra Audience leaves a permanent duplicate.

Any request with two or more known questions belongs in one planned and confirmed multi-question block inside the Study, submitted once rather than as separate direct questions.

Creation is atomic and rolls back partial Audience failures. Studies are private; enabling link sharing also publishes the attached Audiences and their Minds.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes	Name for the Study workspace (e.g., "Brand Perception Study", "Q4 Market Research")
`audienceIds`	No	Preferred field for existing Audience IDs to attach — use list_audiences to find IDs.
`audienceConfigs`	No	Preferred field for new Audiences to create and attach atomically.
`isLinkSharingEnabled`	No	Set true ONLY when the user explicitly asked for a public/shareable Study link. Defaults to false: the Study is private to its owner and no share URL is generated. Enabling this ALSO publishes every attached Audience and every Mind inside them at world-readable URLs — including pre-existing Audiences passed via audienceIds. Do not enable it to "be helpful".

Output Schema

TableJSON Schema

Name	Required	Description
`name`	No	Study name.
`studyId`	No	Created Study.
`replayed`	No	True when an identical request returned the Study created earlier.
`audiences`	No	Audiences attached to the Study.
`workspaceUrl`	No	Authenticated Minds workspace link for the Study.
`publicShareId`	No	Public share identifier, or null.
`sharedStudyUrl`	No	Public share link, or null when link sharing is off.
`isLinkSharingEnabled`	No	Whether the public share link is on.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 22, 2026

removedInput schema / properties / groupConfigs

Removed value: -{
-  "description": "Legacy alias for audienceConfigs.",
-  "items": {
-    "properties": {
-      "mindIds": {
-        "items": {
-          "type": "string"
-        },
-        "type": "array"
-      },
-      "name": {
-        "type": "string"
-      }
-    },
-    "type": "object"
-  },
-  "type": "array"
-}

removedInput schema / properties / groupIds

Removed value: -{
-  "description": "Legacy alias for audienceIds.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

Changed1 schema field changedSep 20, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": {},
+  "properties": {
+    "audiences": {
+      "anyOf": [
+        {
+          "items": {},
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Audiences attached to the Study."
+    },
+    "isLinkSharingEnabled": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Whether the public share link is on."
+    },
+    "name": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Study name."
+    },
+    "publicShareId": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Public share identifier, or null."
+    },
+    "replayed": {
+      "anyOf": [
+        {
+          "type": "boolean"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "True when an identical request returned the Study created earlier."
+    },
+    "sharedStudyUrl": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Public share link, or null when link sharing is off."
+    },
+    "studyId": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Created Study."
+    },
+    "workspaceUrl": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Authenticated Minds workspace link for the Study."
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedSep 9, 2026

changedInput schema / properties / audienceConfigs / items / properties / mindIds / description

Previous value: -"Mind IDs to add to this Audience — use list_minds to find IDs."New value: +"IDs of existing Minds to add to this Audience."

Changed1 schema field changedSep 2, 2026

removedInput schema / properties / groupConfigs / items / properties / sparkIds

Removed value: -{
-  "description": "Legacy alias for mindIds.",
-  "items": {
-    "type": "string"
-  },
-  "type": "array"
-}

Changed5 schema fields changedSep 1, 2026

changedInput schema / properties / groupConfigs / description

Previous value: -"Legacy alias for audienceConfigs. Accepted for compatibility."New value: +"Legacy alias for audienceConfigs."

removedInput schema / properties / groupConfigs / items / properties / mindIds / description
```
Removed value: -"Mind IDs to add to this Audience — use list_minds to find IDs"
```

removedInput schema / properties / groupConfigs / items / properties / name / description

Removed value: -"Audience name (optional — defaults to \"Audience N\"). E.g., \"Gen Z Consumers\", \"Marketing Experts\""

changedInput schema / properties / groupConfigs / items / properties / sparkIds / description

Previous value: -"Legacy alias for mindIds. Accepted for back-compat."New value: +"Legacy alias for mindIds."

changedInput schema / properties / groupIds / description

Previous value: -"Legacy alias for audienceIds. Accepted for compatibility."New value: +"Legacy alias for audienceIds."

AddedAug 27, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Goes far beyond the annotations by disclosing atomic rollback of partial Audience failures, always-creates-new semantics, byte-identical replay behavior with 'replayed: true', permanent no-delete consequences, and link-sharing side effects that publish Audiences and Minds. This rich context helps an agent anticipate side effects that readOnly/destructive hints alone would not convey.

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

Conciseness5/5

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

Dense but every sentence earns its place: core action first, exclusions second, idempotency and irreversible consequences next, then atomicity and privacy. The front-loading of 'does not ask questions or run research' prevents immediate misuse.

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?

Covers all high-stakes aspects an agent needs before calling: idempotency, failure semantics, inability to delete, Audience immutability after creation, multi-question routing, and public-sharing side effects. With an output schema present, the absence of return-format detail is not a 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%, so each parameter is already documented in the schema. The description adds behavioral context (prefer audienceIds, don't enable link sharing unless explicitly requested) but does not need to restate parameter meanings, so the baseline 3 is appropriate.

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?

The description names a specific verb and resource ('Creates a Study workspace') and immediately differentiates from siblings by stating it does not ask questions or run research. This makes it easy for an agent to distinguish create_study from ask_study and run_study_questions.

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

Usage Guidelines5/5

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

Explicitly states when not to use: follow-up research inside an existing Study needs no new Study, and two or more known questions belong in a multi-question block instead of separate direct questions. It also gives prerequisites: settle the Audience set before calling because Audiences cannot be added later and duplicates are permanent.

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.