Skip to main content
Glama
Sign In

Connections

by icu.connections
OverviewDiscussionsAdmin

Switch which workspace this connection uses

connections_switch_workspace
DestructiveIdempotent

Use this the moment the member says they are in the wrong workspace - 'wrong workspace', 'wrong company', 'switch me to ', or when they confirm a switch you offered because data they expected is missing. CALL IT STRAIGHT AWAY WITH NO workspace when they did not name one: if only one other workspace is reachable there is nothing to choose, so it just moves and tells you where it landed - do NOT call connections_list_companies first, and do not ask a question the member has already answered. If several are reachable the reply carries the choices; read those names out, let them pick, and call again with workspace. Moves THIS connection only, effective on the next call, and copies or deletes nothing. Pass remember:true only when they want it to be their preferred workspace (their default in Connections): all their assistants then start there. Say the reply's workspace name back to them.

Input Schema

NameRequiredDescriptionDefault
personNoLinked person to run this call as (first name). Omit to run as the connection's holder.
rememberNoAlso make this the member's preferred workspace (their default in Connections), where all their assistants start. Default false - set it only when they ask for that.
workspaceNocompanyId (preferred) or the exact workspace name. OMIT when the member did not name one - with a single alternative the tool resolves it, with several it hands back the choices to put to them.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / person
      Added value: +{
+  "description": "Linked person to run this call as (first name). Omit to run as the connection's holder.",
+  "type": "string"
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / remember / description
      Previous value: -"Also make this the workspace that any NEW assistant connection starts in. Default false - ask the member before setting it."New value: +"Also make this the member's preferred workspace (their default in Connections), where all their assistants start. Default false - set it only when they ask for that."
  3. Changed1 schema field changed
    • addedInput schema / required
      Added value: +[]
  4. Changed2 schema fields changed
    • changedInput schema / properties / workspace / description
      Previous value: -"companyId (preferred) or the exact workspace name, from connections_list_companies."New value: +"companyId (preferred) or the exact workspace name. OMIT when the member did not name one - with a single alternative the tool resolves it, with several it hands back the choices to put to them."
    • removedInput schema / required
      Removed value: -[
-  "workspace"
-]
  5. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes well past the annotations: it discloses scope ('Moves THIS connection only'), timing ('effective on the next call'), data impact ('copies or deletes nothing'), and the side effect of remember:true (all their assistants then start there). The 'copies or deletes nothing' line sits in mild tension with destructiveHint=true, but reads as clarifying the blast radius rather than contradicting the hint, since switching changes what data the connection sees.

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 trigger condition and the most common case (no workspace named) before the multi-choice branch, so an agent can act on the first clause. It is dense and long for a three-parameter tool, with some repetition ('do not ask a question the member has already answered'), but nearly every sentence carries a distinct instruction.

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?

There is no output schema, and the description compensates by describing what the reply contains in both branches ('it just moves and tells you where it landed'; 'the reply carries the choices'). Combined with the interaction script and the instruction to echo the resulting workspace name, nothing an agent needs to complete the task 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 coverage is 100%, so the baseline is 3; the description earns a 4 by adding decision logic the schema cannot express, namely what to do after an omitted `workspace` returns choices ('read those names out, let them pick, and call again with `workspace`'). It says nothing extra about the `person` parameter, leaving that entirely to the schema.

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 ('switch which workspace this connection uses') and immediately scopes it: 'Moves THIS connection only'. This distinguishes it from connections_list_companies, connections_switch_person, and connections_create_workspace, which are the obvious confusions in the sibling list.

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 trigger phrases ('wrong workspace', 'wrong company', 'switch me to <name>'), an inferred trigger (data they expected is missing), an explicit exclusion ('do NOT call connections_list_companies first'), and a branching procedure for zero-name vs. multiple-name cases. An agent has everything needed to decide when to invoke it and when not to.

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

All Connections 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