Skip to main content
Glama

Pause or resume an integration

set_integration_status
DestructiveIdempotent

Integrations: Use when a signed in customer wants one of their integrations paused or running again (active also switches on a draft once there is a plan). Ask first; a refusal says why. Not for removing one: that is done on its page in CRM Connector.

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": {
      "integration_id": "<integration_id>",
      "status": "<status>"
    },
    "name": "set_integration_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
statusYesactive to run it, paused to stop it.
integration_idYesThe integration's id from list_integrations.

Output Schema

NameRequiredDescriptionDefault
statusNo
messageYes
outcomeYes
conflictsNo
manageUrlNo
integrationIdNo
openConflictsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / integration_id / description
      Previous value: -"The id of the integration, as list_integrations returns it. Ask the person which integration they mean unless they named it in this conversation; never pick one yourself."New value: +"The integration's id from list_integrations."
  2. Changed3 schema fields changed
    • removedOutput schema / properties / choices
      Removed value: -{
      -  "items": {
      -    "properties": {
      -      "id": {
      -        "format": "uuid",
      -        "type": "string"
      -      },
      -      "name": {
      -        "type": "string"
      -      },
      -      "system": {
      -        "type": "string"
      -      },
      -      "systemName": {
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "id",
      -      "system",
      -      "systemName",
      -      "name"
      -    ],
      -    "type": "object"
      -  },
      -  "type": "array"
      -}
    • removedOutput schema / properties / choosePlanUrl
      Removed value: -{
      -  "type": [
      -    "string",
      -    "null"
      -  ]
      -}
    • removedOutput schema / properties / connectLinks
      Removed value: -{
      -  "items": {
      -    "properties": {
      -      "system": {
      -        "type": "string"
      -      },
      -      "systemName": {
      -        "type": "string"
      -      },
      -      "url": {
      -        "type": "string"
      -      }
      -    },
      -    "required": [
      -      "system",
      -      "systemName",
      -      "url"
      -    ],
      -    "type": "object"
      -  },
      -  "type": "array"
      -}
  3. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, idempotentHint=true, and openWorldHint=true, so the safety profile is known. The description adds value beyond them: setting 'active' also switches on a draft, but only once a plan exists — a non-obvious precondition and side effect — and it discloses that refusals carry a reason, which tells the agent to surface that message rather than retry blindly. It does not explain what state a paused integration's in-flight work lands in, so it is not exhaustive.

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?

Three tight sentences, each doing distinct work: scope, prerequisite behavior, and exclusion. The 'Integrations:' prefix and the parenthetical about drafts are slightly awkward to parse but carry real information, so nothing is padding.

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 two-parameter, fully described, idempotent toggle with an output schema and rich annotations, the description supplies the remaining gaps: the draft-activation prerequisite, the confirmation requirement, refusal semantics, and the removal exclusion. An agent could call this correctly and handle the failure case without further information.

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%, and the enum values are already described in-schema, so the baseline of 3 applies. The description does add meaning to the 'active' value by noting it can activate a draft contingent on a plan, but it says nothing extra about integration_id beyond what the schema states ('from list_integrations').

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb pair and resource: pausing or re-running one of the customer's integrations, and it explicitly carves out removal as out of scope. The resource framing ('Integrations:') separates it from sibling toggles like set_automation_status without needing to name them. It stops short of naming an alternative tool for the pause/resume decision itself, but the operation is unambiguous.

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?

It states the triggering situation ('a signed in customer wants one of their integrations paused or running again'), gives a when-not ('Not for removing one: that is done on its page in CRM Connector'), and adds a procedural rule ('Ask first; a refusal says why'). That covers when to use, when to route elsewhere, and the confirmation expectation — everything an agent needs to choose this tool over a neighbor.

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.

Resources