Mnemoverse Memory

memory_create_room

Create a shared memory room so other people's assistants can read and, with read_write access, write shared context across AI tools for team collaboration. Returns the room address for reads/writes.

Instructions

Create a SHARED memory room — a space OTHER people's assistants can read, and write too when their membership scope is read_write, across the AI tools members connect to Mnemoverse. Members can access the room's existing history, including memories saved before they joined; joining does not expose their private account memory. Use when the user wants to share context or collaborate with someone else (e.g. 'make a room for me and my teammate'). Returns the room's address; pass that address as the domain on memory_write/memory_read to use it, and on memory_list_recent to catch up on what others added. People join through an invite minted with memory_invite_to_room.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "name": "<name>"
    },
    "name": "memory_create_room"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes	Room name, unique within your account (e.g. 'launch-team').
`description`	No	Optional description of the room.

Output Schema

Name	Required	Description
`name`	No	The room name as stored.
`address`	Yes	Domain address (xroom:<id>); pass as `domain` on read/write.
`room_id`	Yes	The room's id (room_...); pass to memory_invite_to_room.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.15.3Oct 18, 2026

removedInput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

removedOutput schema / $schema

Removed value: -"http://json-schema.org/draft-07/schema#"

Changed1 schema field changedv0.14.2Oct 1, 2026

changedInput schema / properties / name / description

Previous value: -"Room name, unique within your account (e.g. 'me-and-olya')."New value: +"Room name, unique within your account (e.g. 'launch-team')."

Changed1 schema field changedv0.11.0Sep 23, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "address": {
+      "description": "Domain address (xroom:<id>); pass as `domain` on read/write.",
+      "type": "string"
+    },
+    "name": {
+      "description": "The room name as stored.",
+      "type": "string"
+    },
+    "room_id": {
+      "description": "The room's id (room_...); pass to memory_invite_to_room.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "room_id",
+    "address"
+  ],
+  "type": "object"
+}

Addedv0.5.0Jul 11, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations only say it is a non-destructive, non-readonly create; the description adds substantive behavior an agent could not infer: write access depends on membership scope (read_write), members see history saved before they joined, and joining does not leak private account memory. It also discloses that the result is a room address used as a `domain` handle elsewhere.

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?

The sharing/permission model is front-loaded and the operational follow-through (invite, domain, list) comes after. It is slightly dense and has one overlapping clause ("across the AI tools members connect to Mnemoverse") that could be trimmed without loss.

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?

Only two simple parameters, full schema coverage, an output schema that covers return values, and annotations covering the safety profile. The description still adds the sharing model, membership scope, privacy boundary, and downstream handle usage — the decision-relevant context is complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and both parameters are documented in-schema, so the baseline is 3. The description goes beyond that by explaining the semantic role of the returned address (`domain` on memory_write/memory_read), which is the non-obvious part of using this tool's output as input elsewhere; it adds nothing about the optional `description` parameter.

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 opens with a specific verb+resource ("Create a SHARED memory room") and immediately contrasts it with private memory ("OTHER people's assistants can read", "joining does not expose their private account memory"). This makes it distinguishable from siblings like memory_join_room and memory_list_rooms without opening their schemas.

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?

It states the triggering condition explicitly ("Use when the user wants to share context or collaborate with someone else") with a concrete example utterance. It also points to the follow-on tools: memory_invite_to_room for membership and memory_write/memory_read/memory_list_recent for using the returned address.

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

Deploy Server