campaignstack

campaignstack_extract_recent_comments

Read-only

Read the comments a LinkedIn profile has written, back to a date you name, with the posts they were written on, on one of the workspace's connected accounts. Call this when the user asks what a lead has been commenting on, before drafting outreach that references it. Returns each post's author, body and engagement counts, each comment's text and time, how many replies it drew, and the comment it answered when LinkedIn says so. Reactions are not read. Nothing is written to the other platform and nothing is stored from this read. Reading a LinkedIn account connected to this workspace is free. Any other profile costs 5 credits per LinkedIn call the read makes, and the number of calls cannot be known before the read, because it depends on how densely that person comments: a month of an active commenter is usually 7 to 10 calls. Use maxRequests to cap it. The response reports requestsUsed, stopReason and creditsCharged.

Input Schema

TableJSON Schema

Name	Required	Description
`accountId`	No	Read with a specific connected account. Defaults to the least-loaded one.
`untilDate`	Yes	ISO date to read back to, e.g. 2026-08-10. The walk stops at the first page older than this; comments older than it that share a page are still returned.
`profileUrl`	Yes	LinkedIn profile URL, e.g. https://www.linkedin.com/in/some-slug
`maxRequests`	No	Ceiling on LinkedIn calls, and therefore on the cost. Defaults to 10.
`workspaceId`	No	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.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`code`	No
`error`	No
`posts`	No
`message`	No
`success`	No
`ownAccount`	No
`profileUrl`	No
`profileUrn`	No
`stopReason`	No
`requestsUsed`	No
`creditsCharged`	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": {
+    "code": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "creditsCharged": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "number"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "error": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "message": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "ownAccount": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "boolean"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "posts": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "items": {},
+              "type": "array"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "profileUrl": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "profileUrn": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "requestsUsed": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "number"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "stopReason": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "success": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "boolean"
+            }
+          ]
+        },
+        {
+          "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

A4.7/5.0

Behavior5/5

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

Beyond the readOnlyHint and destructiveHint annotations, the description discloses that nothing is written or stored, that connected-account reads are free while other profiles cost 5 credits per LinkedIn call, and that the call count is unknowable in advance with maxRequests as a cap. It also surfaces requestsUsed, stopReason and creditsCharged, giving full side-effect and cost transparency.

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 long but every sentence earns its place: behavior is front-loaded, then return contents, then cost and stopping behavior. It contains no filler and does not merely restate schema fields.

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 costly paginated read, the description covers what is returned, the cost model, the cap, side effects, account selection, and the output schema is present. Nothing an agent needs to invoke this tool correctly 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 coverage is 100%, so the baseline is 3, but the description adds meaningful context: accountId defaults to the least-loaded account, untilDate stops at the first page older than the date, and maxRequests is framed as the cost ceiling. This helps an agent pick and set parameters more intelligently than the schema alone.

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 first sentence names the exact operation: read comments a LinkedIn profile has written, back to a date, with the posts they were written on, scoped to a connected account. It also explicitly disclaims reading reactions, which distinguishes it from write siblings like campaignstack_comment_on_post and campaignstack_reply_to_comment.

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?

The description gives an explicit trigger: call this when the user asks what a lead has been commenting on, before drafting outreach that references it. It does not name a specific alternative tool or enumerate when-not-to-use conditions, but the context is clear enough to route an agent correctly.

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?