Skip to main content
Glama

campaignstack

by io.campaignstack
OverviewDiscussionsAdmin

Edit workflow

campaignstack_edit_workflow

Create workflows, edit metadata, set whether the workflow sends without review (approvalMode), enable or pause execution, set LinkedIn account pools, set email sender account, set workflow-level outreach intents, and restore a previous node instructions version (restore_guidance, using a versionId from campaignstack_get_workflows include.guidanceHistory). Graph changes belong in campaignstack_edit_workflow_graph. Each operation returns independently.

Input Schema

NameRequiredDescriptionDefault
operationsYesBatch edits are bounded. Return one result per requested item, and report partial failures instead of describing the whole batch as successful.
workspaceIdNoWorkspace ID. Omit it when this connection reaches one workspace: a workspace key (cs_) is bound to its own, and a user key (csu_) or connected app whose person belongs to exactly one workspace defaults to that one. Required only when the person belongs to several; the error then lists them, and campaignstack_whoami reports them too.

Output Schema

NameRequiredDescriptionDefault
okNo
resultsNo
warningsNo
workflowIdNo
workspaceIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / operations / items / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "approvalMode": {
-        "description": "Whether what this workflow drafts waits for a person. manual_review: every message waits in the review queue. auto_when_confident: messages still wait, and the ones the confidence check rates as safe to send unchanged go out on their own once the workspace's calibration allows it (a daily cap applies, and booking confirmations, files, conversation turns and flagged drafts always wait). automatic: no review step at all. On a signal agent this also removes its review steps; on any other workflow, review steps already in the graph keep waiting, so remove them with campaignstack_edit_workflow_graph. Omit to keep the current mode; on create, omit to start from the owner's onboarding answer. Only a workspace owner or admin can set it. Set automatic only when the user asked for messages to go out unreviewed.",
-        "enum": [
-          "manual_review",
-          "auto_when_confident",
-          "automatic"
-        ],
-        "type": "string"
-      },
-      "campaignId": {
-        "type": "string"
-      },
-      "clientOperationId": {
-        "type": "string"
-      },
-      "description": {
-        "type": "string"
-      },
-      "graph": {
-        "additionalProperties": false,
-        "properties": {
-          "anchorEdges": {
-            "items": {
-              "additionalProperties": false,
-              "properties": {
-                "label": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "targetIndex": {
-                  "minimum": 0,
-                  "type": "integer"
-                }
-              },
-              "required": [
-                "targetIndex",
-                "label"
-              ],
-              "type": "object"
-            },
-            "maxItems": 200,
-            "type": "array"
-          },
-          "edges": {
-            "items": {
-              "additionalProperties": false,
-              "properties": {
-                "condition": {},
-                "label": {
-                  "type": "string"
-                },
-                "sourceIndex": {
-                  "minimum": 0,
-                  "type": "integer"
-                },
-                "targetIndex": {
-                  "minimum": 0,
-                  "type": "integer"
-                }
-              },
-              "required": [
-                "sourceIndex",
-                "targetIndex"
-              ],
-              "type": "object"
-            },
-            "maxItems": 200,
-            "type": "array"
-          },
-          "nodes": {
-            "items": {
-              "additionalProperties": false,
-              "properties": {
-                "config": {
-                  "default": {}
-                },
-                "existingNodeId": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "label": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "nodeType": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "position": {
-                  "additionalProperties": false,
-                  "properties": {
-                    "x": {
-                      "type": "number"
-                    },
-                    "y": {
-                      "type": "number"
-                    }
-                  },
-                  "required": [
-                    "x",
-                    "y"
-                  ],
-                  "type": "object"
-                }
-              },
-              "required": [
-                "nodeType",
-                "label"
-              ],
-              "type": "object"
-            },
-            "maxItems": 100,
-            "type": "array"
-          }
-        },
-        "required": [
-          "nodes",
-          "edges"
-        ],
-        "type": "object"
-      },
-      "name": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "op": {
-        "const": "create",
-        "type": "string"
-      },
-      "sourceConfig": {
-        "additionalProperties": {},
-        "type": "object"
-      }
-    },
-    "required": [
-      "op",
-      "name",
-      "sourceConfig",
-      "graph"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "approvalMode": {
-        "$ref": "#/properties/operations/items/anyOf/0/properties/approvalMode",
-        "description": "Whether what this workflow drafts waits for a person. manual_review: every message waits in the review queue. auto_when_confident: messages still wait, and the ones the confidence check rates as safe to send unchanged go out on their own once the workspace's calibration allows it (a daily cap applies, and booking confirmations, files, conversation turns and flagged drafts always wait). automatic: no review step at all. On a signal agent this also removes its review steps; on any other workflow, review steps already in the graph keep waiting, so remove them with campaignstack_edit_workflow_graph. Omit to keep the current mode; on create, omit to start from the owner's onboarding answer. Only a workspace owner or admin can set it. Set automatic only when the user asked for messages to go out unreviewed."
-      },
-      "clientOperationId": {
-        "type": "string"
-      },
-      "description": {
-        "type": "string"
-      },
-      "emailGoogleAccountId": {
-        "anyOf": [
-          {
-            "minLength": 1,
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "name": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "op": {
-        "const": "set_meta",
-        "type": "string"
-      },
-      "outreachIntents": {
-        "items": {
-          "additionalProperties": {},
-          "type": "object"
-        },
-        "maxItems": 20,
-        "type": "array"
-      },
-      "workflowId": {
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "op",
-      "workflowId"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "clientOperationId": {
-        "type": "string"
-      },
-      "enabled": {
-        "type": "boolean"
-      },
-      "op": {
-        "const": "set_enabled",
-        "type": "string"
-      },
-      "workflowId": {
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "op",
-      "workflowId",
-      "enabled"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "accountIds": {
-        "items": {
-          "minLength": 1,
-          "type": "string"
-        },
-        "maxItems": 25,
-        "type": "array"
-      },
-      "clientOperationId": {
-        "type": "string"
-      },
-      "op": {
-        "const": "set_linkedin_accounts",
-        "type": "string"
-      },
-      "workflowId": {
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "op",
-      "workflowId",
-      "accountIds"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "clientOperationId": {
-        "type": "string"
-      },
-      "op": {
-        "const": "restore_guidance",
-        "type": "string"
-      },
-      "versionId": {
-        "description": "versionId of a previous node instructions version to restore.",
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "op",
-      "versionId"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "approvalMode": {
+        "description": "Whether what this workflow drafts waits for a person. manual_review: every message waits in the review queue. auto_when_confident: messages still wait, and the ones the confidence check rates as safe to send unchanged go out on their own once the workspace's calibration allows it (a daily cap applies, and booking confirmations, files, conversation turns and flagged drafts always wait). automatic: no review step at all. On a signal agent this also removes its review steps; on any other workflow, review steps already in the graph keep waiting, so remove them with campaignstack_edit_workflow_graph. Omit to keep the current mode; on create, omit to start from the owner's onboarding answer. Only a workspace owner or admin can set it. Set automatic only when the user asked for messages to go out unreviewed.",
+        "enum": [
+          "manual_review",
+          "auto_when_confident",
+          "automatic"
+        ],
+        "type": "string"
+      },
+      "campaignId": {
+        "type": "string"
+      },
+      "clientOperationId": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "graph": {
+        "additionalProperties": false,
+        "properties": {
+          "anchorEdges": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "label": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "targetIndex": {
+                  "minimum": 0,
+                  "type": "integer"
+                }
+              },
+              "required": [
+                "targetIndex",
+                "label"
+              ],
+              "type": "object"
+            },
+            "maxItems": 200,
+            "type": "array"
+          },
+          "edges": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "condition": {},
+                "label": {
+                  "type": "string"
+                },
+                "sourceIndex": {
+                  "minimum": 0,
+                  "type": "integer"
+                },
+                "targetIndex": {
+                  "minimum": 0,
+                  "type": "integer"
+                }
+              },
+              "required": [
+                "sourceIndex",
+                "targetIndex"
+              ],
+              "type": "object"
+            },
+            "maxItems": 200,
+            "type": "array"
+          },
+          "nodes": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "config": {
+                  "default": {}
+                },
+                "existingNodeId": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "label": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "nodeType": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "position": {
+                  "additionalProperties": false,
+                  "properties": {
+                    "x": {
+                      "type": "number"
+                    },
+                    "y": {
+                      "type": "number"
+                    }
+                  },
+                  "required": [
+                    "x",
+                    "y"
+                  ],
+                  "type": "object"
+                }
+              },
+              "required": [
+                "nodeType",
+                "label"
+              ],
+              "type": "object"
+            },
+            "maxItems": 100,
+            "type": "array"
+          }
+        },
+        "required": [
+          "nodes",
+          "edges"
+        ],
+        "type": "object"
+      },
+      "name": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "op": {
+        "const": "create",
+        "type": "string"
+      },
+      "sourceConfig": {
+        "additionalProperties": {},
+        "type": "object"
+      }
+    },
+    "required": [
+      "op",
+      "name",
+      "sourceConfig",
+      "graph"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "approvalMode": {
+        "$ref": "#/properties/operations/items/anyOf/0/properties/approvalMode",
+        "description": "Whether what this workflow drafts waits for a person. manual_review: every message waits in the review queue. auto_when_confident: messages still wait, and the ones the confidence check rates as safe to send unchanged go out on their own once the workspace's calibration allows it (a daily cap applies, and booking confirmations, files, conversation turns and flagged drafts always wait). automatic: no review step at all. On a signal agent this also removes its review steps; on any other workflow, review steps already in the graph keep waiting, so remove them with campaignstack_edit_workflow_graph. Omit to keep the current mode; on create, omit to start from the owner's onboarding answer. Only a workspace owner or admin can set it. Set automatic only when the user asked for messages to go out unreviewed."
+      },
+      "clientOperationId": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "emailGoogleAccountId": {
+        "anyOf": [
+          {
+            "minLength": 1,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "name": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "op": {
+        "const": "set_meta",
+        "type": "string"
+      },
+      "outreachIntents": {
+        "items": {
+          "additionalProperties": {},
+          "type": "object"
+        },
+        "maxItems": 20,
+        "type": "array"
+      },
+      "workflowId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "op",
+      "workflowId"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "clientOperationId": {
+        "type": "string"
+      },
+      "enabled": {
+        "type": "boolean"
+      },
+      "op": {
+        "const": "set_enabled",
+        "type": "string"
+      },
+      "workflowId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "op",
+      "workflowId",
+      "enabled"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "accountIds": {
+        "description": "Accounts the workflow sends from (LinkedIn account IDs). Omit it to default to the workspace's only LinkedIn account that is ready; with several, the error lists them so you can ask the person. An explicit [] stays empty: the LinkedIn steps send from no account and their leads wait until one is set.",
+        "items": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "maxItems": 25,
+        "type": "array"
+      },
+      "clientOperationId": {
+        "type": "string"
+      },
+      "op": {
+        "const": "set_linkedin_accounts",
+        "type": "string"
+      },
+      "workflowId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "op",
+      "workflowId"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "clientOperationId": {
+        "type": "string"
+      },
+      "op": {
+        "const": "restore_guidance",
+        "type": "string"
+      },
+      "versionId": {
+        "description": "versionId of a previous node instructions version to restore.",
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "op",
+      "versionId"
+    ],
+    "type": "object"
+  }
+]
  2. Changed1 schema field changed
    • changedInput schema / properties / operations / items / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "campaignId": {
-        "type": "string"
-      },
-      "clientOperationId": {
-        "type": "string"
-      },
-      "description": {
-        "type": "string"
-      },
-      "graph": {
-        "additionalProperties": false,
-        "properties": {
-          "anchorEdges": {
-            "items": {
-              "additionalProperties": false,
-              "properties": {
-                "label": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "targetIndex": {
-                  "minimum": 0,
-                  "type": "integer"
-                }
-              },
-              "required": [
-                "targetIndex",
-                "label"
-              ],
-              "type": "object"
-            },
-            "maxItems": 200,
-            "type": "array"
-          },
-          "edges": {
-            "items": {
-              "additionalProperties": false,
-              "properties": {
-                "condition": {},
-                "label": {
-                  "type": "string"
-                },
-                "sourceIndex": {
-                  "minimum": 0,
-                  "type": "integer"
-                },
-                "targetIndex": {
-                  "minimum": 0,
-                  "type": "integer"
-                }
-              },
-              "required": [
-                "sourceIndex",
-                "targetIndex"
-              ],
-              "type": "object"
-            },
-            "maxItems": 200,
-            "type": "array"
-          },
-          "nodes": {
-            "items": {
-              "additionalProperties": false,
-              "properties": {
-                "config": {
-                  "default": {}
-                },
-                "existingNodeId": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "label": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "nodeType": {
-                  "minLength": 1,
-                  "type": "string"
-                },
-                "position": {
-                  "additionalProperties": false,
-                  "properties": {
-                    "x": {
-                      "type": "number"
-                    },
-                    "y": {
-                      "type": "number"
-                    }
-                  },
-                  "required": [
-                    "x",
-                    "y"
-                  ],
-                  "type": "object"
-                }
-              },
-              "required": [
-                "nodeType",
-                "label"
-              ],
-              "type": "object"
-            },
-            "maxItems": 100,
-            "type": "array"
-          }
-        },
-        "required": [
-          "nodes",
-          "edges"
-        ],
-        "type": "object"
-      },
-      "name": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "op": {
-        "const": "create",
-        "type": "string"
-      },
-      "sourceConfig": {
-        "additionalProperties": {},
-        "type": "object"
-      }
-    },
-    "required": [
-      "op",
-      "name",
-      "sourceConfig",
-      "graph"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "clientOperationId": {
-        "type": "string"
-      },
-      "description": {
-        "type": "string"
-      },
-      "emailGoogleAccountId": {
-        "anyOf": [
-          {
-            "minLength": 1,
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "name": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "op": {
-        "const": "set_meta",
-        "type": "string"
-      },
-      "outreachIntents": {
-        "items": {
-          "additionalProperties": {},
-          "type": "object"
-        },
-        "maxItems": 20,
-        "type": "array"
-      },
-      "workflowId": {
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "op",
-      "workflowId"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "clientOperationId": {
-        "type": "string"
-      },
-      "enabled": {
-        "type": "boolean"
-      },
-      "op": {
-        "const": "set_enabled",
-        "type": "string"
-      },
-      "workflowId": {
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "op",
-      "workflowId",
-      "enabled"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "accountIds": {
-        "items": {
-          "minLength": 1,
-          "type": "string"
-        },
-        "maxItems": 25,
-        "type": "array"
-      },
-      "clientOperationId": {
-        "type": "string"
-      },
-      "op": {
-        "const": "set_linkedin_accounts",
-        "type": "string"
-      },
-      "workflowId": {
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "op",
-      "workflowId",
-      "accountIds"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "clientOperationId": {
-        "type": "string"
-      },
-      "op": {
-        "const": "restore_guidance",
-        "type": "string"
-      },
-      "versionId": {
-        "description": "versionId of a previous node instructions version to restore.",
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "op",
-      "versionId"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "approvalMode": {
+        "description": "Whether what this workflow drafts waits for a person. manual_review: every message waits in the review queue. auto_when_confident: messages still wait, and the ones the confidence check rates as safe to send unchanged go out on their own once the workspace's calibration allows it (a daily cap applies, and booking confirmations, files, conversation turns and flagged drafts always wait). automatic: no review step at all. On a signal agent this also removes its review steps; on any other workflow, review steps already in the graph keep waiting, so remove them with campaignstack_edit_workflow_graph. Omit to keep the current mode; on create, omit to start from the owner's onboarding answer. Only a workspace owner or admin can set it. Set automatic only when the user asked for messages to go out unreviewed.",
+        "enum": [
+          "manual_review",
+          "auto_when_confident",
+          "automatic"
+        ],
+        "type": "string"
+      },
+      "campaignId": {
+        "type": "string"
+      },
+      "clientOperationId": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "graph": {
+        "additionalProperties": false,
+        "properties": {
+          "anchorEdges": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "label": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "targetIndex": {
+                  "minimum": 0,
+                  "type": "integer"
+                }
+              },
+              "required": [
+                "targetIndex",
+                "label"
+              ],
+              "type": "object"
+            },
+            "maxItems": 200,
+            "type": "array"
+          },
+          "edges": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "condition": {},
+                "label": {
+                  "type": "string"
+                },
+                "sourceIndex": {
+                  "minimum": 0,
+                  "type": "integer"
+                },
+                "targetIndex": {
+                  "minimum": 0,
+                  "type": "integer"
+                }
+              },
+              "required": [
+                "sourceIndex",
+                "targetIndex"
+              ],
+              "type": "object"
+            },
+            "maxItems": 200,
+            "type": "array"
+          },
+          "nodes": {
+            "items": {
+              "additionalProperties": false,
+              "properties": {
+                "config": {
+                  "default": {}
+                },
+                "existingNodeId": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "label": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "nodeType": {
+                  "minLength": 1,
+                  "type": "string"
+                },
+                "position": {
+                  "additionalProperties": false,
+                  "properties": {
+                    "x": {
+                      "type": "number"
+                    },
+                    "y": {
+                      "type": "number"
+                    }
+                  },
+                  "required": [
+                    "x",
+                    "y"
+                  ],
+                  "type": "object"
+                }
+              },
+              "required": [
+                "nodeType",
+                "label"
+              ],
+              "type": "object"
+            },
+            "maxItems": 100,
+            "type": "array"
+          }
+        },
+        "required": [
+          "nodes",
+          "edges"
+        ],
+        "type": "object"
+      },
+      "name": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "op": {
+        "const": "create",
+        "type": "string"
+      },
+      "sourceConfig": {
+        "additionalProperties": {},
+        "type": "object"
+      }
+    },
+    "required": [
+      "op",
+      "name",
+      "sourceConfig",
+      "graph"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "approvalMode": {
+        "$ref": "#/properties/operations/items/anyOf/0/properties/approvalMode",
+        "description": "Whether what this workflow drafts waits for a person. manual_review: every message waits in the review queue. auto_when_confident: messages still wait, and the ones the confidence check rates as safe to send unchanged go out on their own once the workspace's calibration allows it (a daily cap applies, and booking confirmations, files, conversation turns and flagged drafts always wait). automatic: no review step at all. On a signal agent this also removes its review steps; on any other workflow, review steps already in the graph keep waiting, so remove them with campaignstack_edit_workflow_graph. Omit to keep the current mode; on create, omit to start from the owner's onboarding answer. Only a workspace owner or admin can set it. Set automatic only when the user asked for messages to go out unreviewed."
+      },
+      "clientOperationId": {
+        "type": "string"
+      },
+      "description": {
+        "type": "string"
+      },
+      "emailGoogleAccountId": {
+        "anyOf": [
+          {
+            "minLength": 1,
+            "type": "string"
+          },
+          {
+            "type": "null"
+          }
+        ]
+      },
+      "name": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "op": {
+        "const": "set_meta",
+        "type": "string"
+      },
+      "outreachIntents": {
+        "items": {
+          "additionalProperties": {},
+          "type": "object"
+        },
+        "maxItems": 20,
+        "type": "array"
+      },
+      "workflowId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "op",
+      "workflowId"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "clientOperationId": {
+        "type": "string"
+      },
+      "enabled": {
+        "type": "boolean"
+      },
+      "op": {
+        "const": "set_enabled",
+        "type": "string"
+      },
+      "workflowId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "op",
+      "workflowId",
+      "enabled"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "accountIds": {
+        "items": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "maxItems": 25,
+        "type": "array"
+      },
+      "clientOperationId": {
+        "type": "string"
+      },
+      "op": {
+        "const": "set_linkedin_accounts",
+        "type": "string"
+      },
+      "workflowId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "op",
+      "workflowId",
+      "accountIds"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "clientOperationId": {
+        "type": "string"
+      },
+      "op": {
+        "const": "restore_guidance",
+        "type": "string"
+      },
+      "versionId": {
+        "description": "versionId of a previous node instructions version to restore.",
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "op",
+      "versionId"
+    ],
+    "type": "object"
+  }
+]
  3. Changed1 schema field changed
    • changedInput schema / properties / workspaceId / description
      Previous value: -"Workspace ID. REQUIRED for a user key (csu_), which spans every workspace you belong to; omitted for a workspace key (cs_), which is bound to one and ignores this argument. campaignstack_whoami reports which kind of key you are holding and, for a user key, the workspaces it can reach."New value: +"Workspace ID. Omit it when this connection reaches one workspace: a workspace key (cs_) is bound to its own, and a user key (csu_) or connected app whose person belongs to exactly one workspace defaults to that one. Required only when the person belongs to several; the error then lists them, and campaignstack_whoami reports them too."
  4. Added

TDQS

A4.1/5.0
Behavior3/5

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

Annotations already declare the mutability profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), reducing the description's burden. The description adds the useful behavioral note that each operation returns independently, but does not add much else beyond annotations, such as permission requirements, rate limits, or irreversible effects.

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?

The description is front-loaded with the tool's operations and includes the key sibling routing directly afterward. The first sentence is a long enumerated list, which is dense but earns its place by covering the tool's full scope without filler.

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?

Given the high-complexity batch schema and the presence of an output schema, the description is largely complete: it names all operation families, routes graph edits to the sibling, and explains the restore version source. It omits details like batch bounds, partial-failure semantics, and workspace scoping, but those are supplied by the schema and output schema.

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?

With 100% schema description coverage, the baseline is 3, but the description adds meaning by naming several operations and clarifying that restore_guidance takes a versionId sourced from campaignstack_get_workflows include.guidanceHistory. It also translates some schema fields into plain language, such as email sender account and workflow-level outreach intents.

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?

The description names a specific resource (workflow) and enumerates the exact operation types it supports, including create, metadata edits, approval mode, execution state, LinkedIn account pools, email sender, outreach intents, and guidance restore. It also explicitly distinguishes itself from campaignstack_edit_workflow_graph, so an agent can separate the two 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 Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives a clear routing rule for graph changes, directing them to campaignstack_edit_workflow_graph, and notes that restore_guidance needs a versionId from campaignstack_get_workflows include.guidanceHistory. However, it does not provide broader when-to-use or when-not guidance for the many other operation types relative to other workflow tools.

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

All campaignstack 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