Skip to main content
Glama
Sign In

Connections

by icu.connections
OverviewDiscussionsAdmin

Sign this connection out of Connections

connections_signout
DestructiveIdempotent

Use this ONLY when the member says they are signed in as the WRONG Connections account and want to sign out or switch account. Ends this connection's Connections session for good: every tool here stops working until they reconnect, and reconnecting is a few clicks in their assistant's own settings. Set confirm only once the member has confirmed in plain words, and if they only want a different WORKSPACE on the same account use connections_switch_workspace instead - that needs no sign-out at all. The reply carries the exact reconnect steps for their assistant; read them back verbatim, because this is the last answer this connection can give.

Input Schema

NameRequiredDescriptionDefault
personNoLinked person to run this call as (first name). Omit to run as the connection's holder.
confirmYesMust be true. Set it only after the member has confirmed in words that they want to sign out.
projectNoWorkspace to run this call in (id or name).

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
    • addedInput schema / properties / project
      Added value: +{
+  "description": "Workspace to run this call in (id or name).",
+  "type": "string"
+}
  3. Added

TDQS

A4.7/5.0
Behavior5/5

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

Annotations say destructiveHint=true, but the description supplies the part annotations cannot: what actually breaks ('every tool here stops working until they reconnect'), how recovery works ('reconnecting is a few clicks in their assistant's own settings'), and that the reply is the final message this connection can produce. That last point is critical behavior an agent would otherwise get wrong.

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?

Four sentences, each load-bearing: trigger, consequence, confirmation/alternative routing, and how to handle the reply. The gating condition is front-loaded in capitals so it is the first thing an agent reads.

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?

No output schema exists, and the description compensates by telling the agent what the reply contains (exact reconnect steps) and what to do with it (read back verbatim). Nothing needed to call this destructive tool safely is missing.

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 coverage is 100%, so all three parameters are already documented, and the description's guidance for `confirm` largely restates the schema text. It says nothing about `person` or `project` (running as another person or in a workspace), which is where extra meaning could have been added.

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?

Precise verb and resource ('sign out / ends this connection's Connections session') with an explicit scope limiter ('ONLY when the member says they are signed in as the WRONG account'). It distinguishes itself from connections_switch_workspace by name, so an agent can route without opening either schema.

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?

States the exact trigger condition, the near-miss case that should NOT use it ('if they only want a different WORKSPACE ... use connections_switch_workspace instead'), and the prerequisite that the member must confirm in plain words first. This is when/when-not/alternative in three sentences.

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