Gnosis Memory

collection_manage

Destructive

Manage shared collections (multi-user memory folders).

list: your collections + invites. create. update: rename (display only; slug/keys unchanged). delete: owner only, 2-step -- call without confirm to see impact + token, repeat with confirm:"". Permanent. members: who's in it. add_user / remove_user: by email or agent name. accept / decline an invite. publish: copy personal memories into it by id (originals kept). leave: remove YOURSELF from a collection you are a member of. Owners use delete. convert: flip type with type:"collaborative"|"knowledge_pack". ->collaborative mints a K_user wrap for each PIN-holding active member; ->knowledge_pack is a label flip. No wrap or DEK row is ever deleted either way.

Write to one: collection:"name" in memory_add. Search auto-includes all your collections.

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": {
      "action": "<action>"
    },
    "name": "collection_manage"
  }
}

Input Schema

Name	Required	Description
`name`	No	Collection name.
`role`	No	"admin" = manages the collection (owner or admin may grant; the invitee needs a PIN to accept), "member" = can read and write, "reader" = can only read. Default: member.
`type`	No	"collaborative" = everyone can read and write. "knowledge_pack" = only the owner writes, others can read. Default: collaborative.
`user`	No	Email or agent name to add/remove.
`action`	Yes	What to do
`confirm`	No	delete: 2-step. Call without it -> refusal names slug + member/memory impact; repeat with confirm:"<slug>". Permanent.
`new_name`	No	update: new display name (slug/keys unchanged). Type change not via update.
`memory_ids`	No	Memory IDs to publish (copy in; originals kept).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and readOnlyHint=false, so the safety bar is lower, yet the description still adds real context: delete is permanent and two-phase, publish copies with originals kept, convert's directional effects (a K_user wrap is minted, and no wrap or DEK row is ever deleted), and rename leaves slug/keys untouched. It stops short of stating what list/members return, but the mutation semantics are unusually well disclosed.

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?

Front-loaded with the resource, then a compact per-action key/value layout that scans efficiently despite packing twelve actions into one paragraph. The final "Write to one" line is a high-value cross-tool hint rather than filler, though the fragment style ("create.", "actions:") is terse to the point of near-cryptic for a first-time reader.

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 a 12-action, 8-parameter dispatcher with no output schema, the description covers the destructive and irreversible paths thoroughly and warns about owner-only operations. Minor gaps remain around return shapes for list/members and whether accept requires a PIN (that detail lives only in the schema), but nothing an agent needs to invoke it safely is missing.

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 description coverage is 100%, so the baseline is 3, but the description adds cross-parameter meaning the schema does not: `user` accepts email or agent name, `memory_ids` copies rather than moves, and the `type` enum's two values map to distinct cryptographic consequences. It also clarifies that the collection identifier is used from `memory_add`, which is outside this schema entirely.

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+resource ("Manage shared collections (multi-user memory folders)") and then enumerates all twelve actions with their individual effects, so the agent knows exactly what each value of `action` does. It also distinguishes itself from siblings by routing writes to memory_add with `collection:"name"` and noting search auto-includes collections.

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?

Gives explicit per-action routing rules and exclusions: "leave: remove YOURSELF... Owners use delete", "update: rename (display only; slug/keys unchanged)", "Type change not via update" alongside `convert`. The 2-step delete protocol (call without confirm, then repeat with the token) is spelled out as a procedure, not left to inference.

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

All Gnosis Memory 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.

Resources

Need Help?