campaignstack

campaignstack_onboard_workspace

Set up a CampaignStack workspace: who the user works for, what that company sells, why it exists, how they write, and who they sell to.

Call this with no arguments FIRST. It returns what CampaignStack already knows, including the employer company resolved from the user's LinkedIn profile and any facts already gathered on it, plus every field you can write and its current value. Read that before you propose anything: your job is to correct and complete what is there, not to describe the company from scratch.

Then call it again with the fields you are confident about. Confidence means you can point to something specific: their profile, their company page, their site, something they told you. When you are not confident about a field, leave it out. An empty field is fixed in ten seconds by the user. A plausible sentence that is wrong gets read into every message the system writes for them, and nobody catches it until a prospect does.

Report back in plain language what you set and what you left empty, so the user can correct you before any of it reaches a message.

Input Schema

TableJSON Schema

Name	Required	Description
`voice`	No	How this person writes: sentence length, formality, punctuation habits, phrases they reuse. Describe, never instruct.
`firstIcp`	No	A first ideal customer profile. At least one list is required for it to be written.
`whatWeSell`	No	What the company sells, in one or two plain sentences. Facts only.
`companyName`	No	The company the user works for.
`workspaceId`	No	Defaults to the workspace the extension set up for this key, or the key's workspace.
`whyWeBuiltIt`	No	Why the company exists: the specific thing the founder saw that made it worth building. Omit unless it is concrete and checkable.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`next`	No
`note`	No
`state`	No
`written`	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": {
+    "next": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "note": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "type": "string"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "state": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "additionalProperties": true,
+              "properties": {
+                "agentWrittenUnconfirmed": {
+                  "anyOf": [
+                    {
+                      "anyOf": [
+                        {
+                          "not": {}
+                        },
+                        {
+                          "items": {
+                            "type": "string"
+                          },
+                          "type": "array"
+                        }
+                      ]
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "caps": {
+                  "anyOf": [
+                    {
+                      "anyOf": [
+                        {
+                          "not": {}
+                        },
+                        {}
+                      ]
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "employerCompany": {
+                  "anyOf": [
+                    {
+                      "anyOf": [
+                        {
+                          "not": {}
+                        },
+                        {}
+                      ]
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "fields": {
+                  "anyOf": [
+                    {
+                      "anyOf": [
+                        {
+                          "not": {}
+                        },
+                        {}
+                      ]
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "linkedinProfile": {
+                  "anyOf": [
+                    {
+                      "anyOf": [
+                        {
+                          "not": {}
+                        },
+                        {}
+                      ]
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                },
+                "workspaceId": {
+                  "anyOf": [
+                    {
+                      "anyOf": [
+                        {
+                          "not": {}
+                        },
+                        {
+                          "type": "string"
+                        }
+                      ]
+                    },
+                    {
+                      "type": "null"
+                    }
+                  ]
+                }
+              },
+              "type": "object"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "written": {
+      "anyOf": [
+        {
+          "anyOf": [
+            {
+              "not": {}
+            },
+            {
+              "items": {
+                "type": "string"
+              },
+              "type": "array"
+            }
+          ]
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}

AddedSep 18, 2026
RemovedSep 6, 2026
AddedSep 4, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With all annotations false, the description carries the full burden, and it delivers: it discloses the non-obvious read-modify-write pattern, that the no-argument call returns the employer resolved from LinkedIn plus current field values, and the rule that unconfident fields must be omitted. It also explains the real consequence of a wrong guess (plausible errors get read into outbound messages). The one gap is that it never explicitly states whether a partial second call merges with or overwrites existing field values, though 'correct and complete what is there' implies a merge.

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?

Four short paragraphs follow the workflow in strict order: what the tool does, first call, second call, reporting. The opening sentence front-loads the purpose, and the roughly 220-word length is proportionate to a two-phase tool with 6 parameters and a nested object; the consequence-framing sentences earn their place because they change agent behavior toward safe omission.

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?

The description fully specifies the non-obvious two-phase protocol, what the first call returns, the confidence threshold, and the required plain-language report, while the output schema covers the write call's return value. Nothing an agent needs to invoke this correctly is missing; the only soft spot, merge-versus-overwrite semantics, is resolved well enough by 'correct and complete what is there.'

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 parameter-level guidance the schema cannot express: omit any field you cannot support with evidence, because an empty field is cheap to fix while a plausible wrong one is costly. It also maps the five onboarding questions to the parameter groups (companyName, whatWeSell, whyWeBuiltIt, voice, firstIcp), reinforcing which parameters serve which goal.

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-resource pair ('Set up a CampaignStack workspace') and enumerates the exact scope of what gets configured: the employer, what the company sells, why it exists, how the user writes, and who they sell to. The two-phase read-then-write framing further separates it from siblings like update_workspace or get_workspace_setup, so an agent can tell this onboarding flow apart without inspecting those tools.

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 invocation protocol: 'Call this with no arguments FIRST,' then call again with only confident fields, then 'Report back in plain language what you set and what you left empty.' It also states the confidence standard (point to a profile, company page, site, or something the user said). However, it never names alternative tools or states when not to use this one in favor of a sibling, so it stops short of full exclusion guidance.

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?