campaignstack

campaignstack_request_connect_link

A link the user clicks to connect a NEW LinkedIn or Google account. Connecting is a browser step by design: LinkedIn needs a session the extension captures, Google needs its consent screen, and neither a cookie nor a password should ever be pasted into a chat. For LinkedIn the link is the accounts page (with the extension the connect is one click; without it, an email and password or a session cookie entered on that page). For Google the link is a consent URL minted for this user, valid ten minutes. Send the link, then poll campaignstack_list_accounts until the account appears, and link it to the right workspace with campaignstack_link_account_to_workspace if it is not there already. Never ask the user for their credentials.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`platform`	Yes	Which kind of account to connect.
`workspaceId`	No	Optional. Where the person lands after connecting; defaults to the accounts page.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`url`	No
`next`	No
`platform`	No
`expiresAt`	No
`extensionUrl`	No
`instructions`	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": {
+    "expiresAt": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "number"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "extensionUrl": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "instructions": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "next": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "platform": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "url": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

AddedSep 18, 2026

TDQS

A4.9/5.0

Behavior5/5

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

With only sparse annotations, the description carries the behavioral burden and does so well: it discloses the browser-step design, Google's ten-minute consent URL expiry, LinkedIn's accounts-page fallback, and the rule that cookies and passwords never enter chat. It adds substantial context beyond the annotations without contradicting them.

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?

The description is longer than average but every sentence carries new operational information: platform differences, expiry, follow-up polling, workspace linking, and credential safety. It is front-loaded with the core purpose and wastes no words.

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?

Given the output schema exists and the input schema is small, the description fully covers what the agent needs: what the link is, how each platform behaves, how to validate completion, and how to finish the workflow. Nothing needed for correct invocation 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?

The schema already covers both parameters at 100%, so the baseline is 3. The description adds value by explaining what each platform link actually is and clarifying that workspaceId controls where the person lands, which maps usefully onto the optional 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 states a specific verb and resource: it produces a link the user clicks to connect a NEW LinkedIn or Google account. It distinguishes this from integration tools for other platforms by naming the exact platforms and the browser-step mechanism.

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 explicitly explains when to use the tool, what to do afterwards (poll campaignstack_list_accounts, then link to workspace if needed), and what never to do (never ask for credentials). It also gives platform-specific expectations for the user flow.

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?