campaignstack

campaignstack_get_account_safety

Read-onlyIdempotent

Read the safety measurement of a LinkedIn account: what LinkedIn saw the account do on the previous complete day, split into what CampaignStack sent (ours) and what somebody else sent (foreign), per write type (connection_request, send_message, post_comment). Headroom is LinkedIn's daily ceiling minus the foreign volume, and it caps what CampaignStack dispatches today (actions[].dispatchable). The measured floor is the account's own trailing volume over the last 28 days, which the ramp-up never decays below (actions[].floor). A null foreign means the signal was not measured and nothing is subtracted. Also returns the last 28 measured days (days[]), the pending-invitation backlog by age, the weekly invitation cap fact, the weekly acceptance series, the unmeasured signals and the safety score with its parts. Carries no reply rate and no message detail: reply rate is shown only on the account page inside the CampaignStack app, never here or in any other tool. Use campaignstack_list_accounts to find account IDs. Call this when an account might be at risk, or before raising its volume: it separates CampaignStack's own sends from the rest.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`workspaceId`	Yes	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.
`linkedinAccountId`	Yes

Output Schema

TableJSON Schema

Name	Required	Description
`days`	No	28-day daily series of observed/ours/foreign per type
`tier`	No
`flags`	No
`score`	No
`status`	No
`actions`	No	Per write-type headroom, dispatchable and floor
`backlog`	No	Pending-invitation backlog by age
`pending`	No
`budgetDay`	No
`weeklyCap`	No
`acceptance`	No
`measuredAt`	No
`unmeasured`	No
`commentsPerWeek`	No
`connectionsCount`	No
`linkedinAccountId`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 20, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "acceptance": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "items": {},
+              "type": "array"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "actions": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "items": {},
+              "type": "array"
+            }
+          ],
+          "description": "Per write-type headroom, dispatchable and floor"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Per write-type headroom, dispatchable and floor"
+    },
+    "backlog": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "anyOf": [
+                {},
+                {
+                  "type": "null"
+                }
+              ]
+            }
+          ],
+          "description": "Pending-invitation backlog by age"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "Pending-invitation backlog by age"
+    },
+    "budgetDay": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": [
+                "string",
+                "null"
+              ]
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "commentsPerWeek": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": [
+                "number",
+                "null"
+              ]
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "connectionsCount": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": [
+                "number",
+                "null"
+              ]
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "days": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "items": {},
+              "type": "array"
+            }
+          ],
+          "description": "28-day daily series of observed/ours/foreign per type"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "28-day daily series of observed/ours/foreign per type"
+    },
+    "flags": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {}
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "linkedinAccountId": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "measuredAt": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": [
+                "number",
+                "null"
+              ]
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "pending": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "boolean"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "score": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {}
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "status": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": [
+                "string",
+                "null"
+              ]
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "tier": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "unmeasured": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "weeklyCap": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": [
+                "number",
+                "null"
+              ]
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedSep 13, 2026

addedInput schema / properties / workspaceId / description

Added 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."

AddedSep 9, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so the description aligns. It adds valuable behavioral context beyond annotations: explains what a null foreign means ('signal was not measured and nothing is subtracted'), defines headroom and floor, and lists the full return set (days[], pending backlog, weekly cap, etc.). It also explicitly states what is NOT returned, which is transparency beyond the schema.

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 long but every sentence serves a purpose: it defines core concepts, lists outputs, explains null semantics, and gives usage triggers. It front-loads the primary purpose and the most critical distinction (ours vs. foreign). While dense, it is efficiently organized and not redundant with the schema.

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 complex read tool with many output fields, the description is remarkably complete. It explains the meaning of key metrics (headroom, floor, dispatchable), the interpretation of nulls, the full set of returned data, and what is deliberately omitted. It also provides usage context and a sibling pointer. Nothing an agent needs to decide to call this tool 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 description coverage is 50%: workspaceId is thoroughly described in the schema, but linkedinAccountId has only a name. The description compensates by telling the agent to use campaignstack_list_accounts to find account IDs, giving practical guidance for the second parameter. It doesn't duplicate schema content but adds value for the undocumented parameter.

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 opens with a specific verb and resource: 'Read the safety measurement of a LinkedIn account.' It then enumerates the exact breakdown (ours vs. foreign per write type) and key outputs (headroom, floor, days[]), making the tool's purpose unambiguous and distinct from siblings. It even states what it does NOT carry (reply rate, message detail), further differentiating it.

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?

The description gives explicit when-to-use guidance: 'Call this when an account might be at risk, or before raising its volume.' It also explains the key decision factor (separating own sends from foreign) and points to campaignstack_list_accounts for finding account IDs. It clarifies that reply rate is never available here or in any other tool, setting clear expectations.

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

All campaignstack tools Inspect

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

Need Help?