Skip to main content
Glama

ctxstore — memory that follows you across models

Switch Workspace

switch_workspace
Idempotent

Narrow this session's memory to one project: name='' scopes recall, the wake bundle, self-notes and the default namespace for new facts to project::* (identity and conventions always ride along). Returns the narrowed bundle right away. name='' widens back to the whole account. Sticky for the session and across reconnects; bind_agent is unaffected. The same call ENTERS a workspace someone shared with this account: name='' (or their tenant id, or the granted prefix, as listed by list_workspaces) switches this connection into it; no second server, no header, no restart; it holds for the session. name='' leaves it for the session. HOME WORKSPACE: remember=true also makes it this account's home, so every new session starts inside it; switch_workspace(name='', forget=true) forgets the home. An account with no facts of its own and exactly one shared workspace starts inside that workspace automatically. list_workspaces and wake_status show the home and how this session entered (home, tool or header). When a person asks to work in someone else's shared memory, call this.

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": "switch_workspace"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesProject slug (the <slug> in project:<slug>:*), the name of a granted workspace to enter (from list_workspaces), or '' to widen / leave.
forgetNoWith name='': also forget the home workspace, so new sessions start in your own account (the automatic home included).
rememberNoWith a granted workspace's name: also make it the home workspace, entered at the start of every new session.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / forget
      Added value: +{
      +  "description": "With name='': also forget the home workspace, so new sessions start in your own account (the automatic home included).",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / remember
      Added value: +{
      +  "description": "With a granted workspace's name: also make it the home workspace, entered at the start of every new session.",
      +  "type": "boolean"
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / name / description
      Previous value: -"Project slug (the <slug> in project:<slug>:*), or '' to widen."New value: +"Project slug (the <slug> in project:<slug>:*), the name of a granted workspace to enter (from list_workspaces), or '' to widen / leave."
  3. First observed

TDQS

A4.6/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, idempotentHint=true, destructiveHint=false, and the description adds genuinely non-obvious behavior: the narrowing is sticky for the session and across reconnects, the narrowed bundle is returned immediately, identity/conventions always ride along, and the automatic single-shared-workspace home case. What's missing is any caveat about permission failures (e.g., what happens if the named workspace wasn't granted), which matters for a mutation-flagged 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?

Front-loaded with the core effect and the widening case before the shared-workspace and home sections, and the "no second server, no header, no restart" phrasing earns its place by preempting a wrong mental model. It is dense and slightly repetitive on stickiness ("sticky for the session" restated as "it holds for the session"), which keeps it from a 5.

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?

For a 3-parameter state-mutating tool with no output schema, the description covers effect scope, persistence, return behavior ("returns the narrowed bundle right away"), exit path, and the home-workspace lifecycle. An agent has everything needed to call it correctly and to predict the session's subsequent state.

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%, so a 3 is the baseline, but the description adds meaning the schema doesn't: name accepts a project slug, a granted workspace's display name, its tenant id, or its granted prefix, and the empty string has two distinct outcomes depending on forget. The remember=true home-workspace interaction with forget=true is spelled out rather than left to inference.

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 — narrows this session's memory to one project, and additionally enters a shared/granted workspace. It also names the exact things affected (recall, wake bundle, self-notes, default namespace for new facts) and explicitly contrasts with bind_agent, so an agent can distinguish it from siblings without opening 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?

Gives explicit when-to-use instructions: "When a person asks to work in someone else's shared memory, call this," plus the reverse case name='' to widen/leave and name='' with forget=true to drop the home. It names list_workspaces and wake_status as the tools that reveal home/entry mode, so the routing decision is fully covered.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.