Skip to main content
Glama

Mnemoverse Memory

by io.github.mnemoverse
OverviewDiscussionsAdmin

memory_create_room

Create a SHARED memory room — a space OTHER people's assistants can read, and write too when their invite granted read_write (the default scope), across Claude/ChatGPT/Cursor. Use when the user wants to share context or collaborate with someone else (e.g. 'make a room for me and Olya'). 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. To bring someone in, call memory_invite_to_room next.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesRoom name, unique within your account (e.g. 'me-and-olya').
descriptionNoOptional description of the room.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameNoThe room name as stored.
addressYesDomain address (xroom:<id>); pass as `domain` on read/write.
room_idYesThe room's id (room_...); pass to memory_invite_to_room.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / additionalProperties
      Removed value: -false
    • changedInput schema / properties / description / description
      Previous value: -"Optional human description of the room."New value: +"Optional description of the room."
    • changedOutput schema / required
      Previous value: -[
-  "room_id",
-  "address",
-  "name"
-]New value: +[
+  "room_id",
+  "address"
+]
  2. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only say the tool is not read-only, not open-world, not idempotent, and not destructive. The description adds meaningful behavior: default invite scope is read_write, other assistants can read and write, and the return value is the room's address. This goes well beyond annotation hints, though it does not cover edge cases like duplicate names or failure behavior.

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?

The description is longer than average, but every sentence earns its place: shared semantics, default permissions, when to use it, return-value usage, and the next recommended action. No filler or redundant restatement of the schema.

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 description covers what the tool does, why it exists, how to use the result across sibling tools, and what action to take next. With only two parameters and an output schema present, nothing essential is missing for an agent to invoke this tool correctly.

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 the input schema already fully documents the `name` and `description` parameters. The description does not add significant new parameter-level meaning beyond restating the name example and the uniqueness constraint already present in the schema. 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 opens with a specific verb and resource: 'Create a SHARED memory room.' It clearly distinguishes this from other sibling tools by emphasizing the shared/collaborative aspect and by explaining that the returned address is used as a `domain` on memory_write/memory_read and memory_list_recent. The example 'make a room for me and Olya' anchors the intent unambiguously.

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?

The description explicitly states when to use this tool ('Use when the user wants to share context or collaborate with someone else'), and it names the next logical step, memory_invite_to_room. It also explains how to use the result with sibling tools. It does not explicitly state when not to use it or contrast it against a close alternative, but the shared-vs-private distinction is strongly implied.

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

All Mnemoverse Memory toolsInspect
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.

Resources