Skip to main content
Glama

campaignstack

by io.campaignstack
OverviewDiscussionsAdmin

campaignstack_edit_competitor_watch

Destructive

Create competitor watches, pause/resume them, assign LinkedIn accounts used by CampaignStack to observe those competitors, or delete them. Omit sendAccountIds (or pass []) to collect engagers without contacting anyone. A delete operation runs the same removal as campaignstack_delete_competitor_watch and requires confirmed:true on that operation. Batch edits are bounded. Return one result per requested item, and report partial failures instead of describing the whole batch as successful.

Input Schema

NameRequiredDescriptionDefault
operationsYes
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
resultsNo
warningsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / operations / items / anyOf
      Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "entityType": {
-        "enum": [
-          "company",
-          "influencer"
-        ],
-        "type": "string"
-      },
-      "linkedinAccountIds": {
-        "description": "Reads with: LinkedIn account IDs that open watched competitor pages and collect engagers. Defaults to backend automatic selection.",
-        "items": {
-          "minLength": 1,
-          "type": "string"
-        },
-        "maxItems": 25,
-        "type": "array"
-      },
-      "linkedinUrl": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "mode": {
-        "const": "create",
-        "type": "string"
-      },
-      "name": {
-        "minLength": 1,
-        "type": "string"
-      },
-      "sendAccountIds": {
-        "description": "Sends from: LinkedIn account IDs the engagers hear from when the watch creates a new signal agent. Omit to collect engagers without contacting anyone.",
-        "items": {
-          "minLength": 1,
-          "type": "string"
-        },
-        "maxItems": 25,
-        "type": "array"
-      }
-    },
-    "required": [
-      "mode",
-      "linkedinUrl",
-      "name",
-      "entityType"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "mode": {
-        "const": "set_status",
-        "type": "string"
-      },
-      "status": {
-        "enum": [
-          "active",
-          "paused"
-        ],
-        "type": "string"
-      },
-      "watchId": {
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "mode",
-      "watchId",
-      "status"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "linkedinAccountIds": {
-        "items": {
-          "minLength": 1,
-          "type": "string"
-        },
-        "maxItems": 25,
-        "type": "array"
-      },
-      "mode": {
-        "const": "set_accounts",
-        "type": "string"
-      },
-      "watchId": {
-        "minLength": 1,
-        "type": "string"
-      }
-    },
-    "required": [
-      "mode",
-      "watchId",
-      "linkedinAccountIds"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "entityType": {
+        "enum": [
+          "company",
+          "influencer"
+        ],
+        "type": "string"
+      },
+      "linkedinAccountIds": {
+        "description": "Reads with: LinkedIn account IDs that open watched competitor pages and collect engagers. Defaults to backend automatic selection.",
+        "items": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "maxItems": 25,
+        "type": "array"
+      },
+      "linkedinUrl": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "mode": {
+        "const": "create",
+        "type": "string"
+      },
+      "name": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "sendAccountIds": {
+        "description": "Sends from: LinkedIn account IDs the engagers hear from when the watch creates a new signal agent. Omit sendAccountIds (or pass []) to collect engagers without contacting anyone.",
+        "items": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "maxItems": 25,
+        "type": "array"
+      }
+    },
+    "required": [
+      "mode",
+      "linkedinUrl",
+      "name",
+      "entityType"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "mode": {
+        "const": "set_status",
+        "type": "string"
+      },
+      "status": {
+        "enum": [
+          "active",
+          "paused"
+        ],
+        "type": "string"
+      },
+      "watchId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "mode",
+      "watchId",
+      "status"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "linkedinAccountIds": {
+        "description": "Reads with: accounts that open the watched page (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.",
+        "items": {
+          "minLength": 1,
+          "type": "string"
+        },
+        "maxItems": 25,
+        "type": "array"
+      },
+      "mode": {
+        "const": "set_accounts",
+        "type": "string"
+      },
+      "watchId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "mode",
+      "watchId"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "confirmed": {
+        "const": true,
+        "description": "This permanently deletes a root record. Before calling it, name exactly what will be deleted, explain that it cannot be undone, and wait for an explicit yes.",
+        "type": "boolean"
+      },
+      "mode": {
+        "const": "delete",
+        "type": "string"
+      },
+      "watchId": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "mode",
+      "watchId",
+      "confirmed"
+    ],
+    "type": "object"
+  }
+]
  2. 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."
  3. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and non-idempotent, and the description adds real detail beyond them: which operation is destructive (delete), the confirmed:true gate, that batch edits are bounded, and that results report partial failures rather than a blanket success. It does not quantify the batch bound or describe permission requirements.

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 verbs are front-loaded in the first sentence, and the follow-on sentences each carry a distinct operational fact (opt-out sending, delete confirmation, batch result semantics). It is dense but every sentence earns its place, with only mild verbosity in the account-assignment phrasing.

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?

For a multiplexed write tool with a rich anyOf schema and an output schema, the description supplies the missing operational context: per-mode behavior, delete confirmation, batch bounding, and partial-failure reporting. Return-value detail is correctly left to the output schema, so coverage is largely complete.

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 around 50% and the description mostly restates schema-level semantics for sendAccountIds (omit/[] to avoid contacting engagers) rather than adding new meaning. It does not clarify the mode enum values or the workspaceId resolution behavior from a description standpoint, so it only partially compensates for the coverage gap.

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 the resource (competitor watches) and enumerates the specific operations the tool performs: create, pause/resume, assign observing LinkedIn accounts, and delete. It also differentiates from the sibling by noting that delete runs the same removal as campaignstack_delete_competitor_watch, so an agent can place the tool 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 Guidelines4/5

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

It gives clear situational context for each mode and explicitly routes the delete case via a named sibling plus a required confirmed:true precondition. It stops short of stating when NOT to use this tool (e.g. versus get_competitor_watches for reads), so it is clear but not exhaustive.

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