Skip to main content
Glama

campaignstack

by io.campaignstack
OverviewDiscussionsAdmin

Edit workspace

campaignstack_edit_workspace

Write workspace settings, branding, compliance, restore one playbook version, or accept/reject the pending playbook proposal. Only supplied components change. Branding affects client-facing shared artifacts only; compliance toggles the fixed lawful-basis notice; playbook restores are versioned. Read the pending proposal with campaignstack_get_workspaces' playbookProposal include before deciding it.

Input Schema

NameRequiredDescriptionDefault
brandingNo
settingsNo
complianceNo
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.
proposalDecisionNo
restorePlaybookVersionIdNo

Output Schema

NameRequiredDescriptionDefault
okNo
resultsNo
warningsNo
workspaceIdNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / settings / properties / companyProfile
      Added value: +{
+  "additionalProperties": false,
+  "description": "The company facts the playbook asks for. null clears one.",
+  "properties": {
+    "businessModel": {
+      "anyOf": [
+        {
+          "maxLength": 2000,
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "deliverables": {
+      "anyOf": [
+        {
+          "maxLength": 2000,
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "whatWeAreNot": {
+      "anyOf": [
+        {
+          "maxLength": 2000,
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "whatWeDo": {
+      "anyOf": [
+        {
+          "maxLength": 2000,
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "whyWeBuiltIt": {
+      "anyOf": [
+        {
+          "maxLength": 2000,
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    }
+  },
+  "type": "object"
+}
  2. Changed1 schema field changed
    • addedInput schema / properties / settings / properties / jevFeatures / properties / callbackTiming
      Added value: +{
+  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
+}
  3. Changed12 schema fields changed
    • changedInput schema / properties / settings / properties / jevFeatures / properties / agentGuard / $ref
      Previous value: -"#/properties/settings/properties/jevFeatures/properties/replyIntent"New value: +"#/properties/settings/properties/jevFeatures/properties/confidenceGate"
    • addedInput schema / properties / settings / properties / jevFeatures / properties / applicationPrefill
      Added value: +{
+  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
+}
    • changedInput schema / properties / settings / properties / jevFeatures / properties / briefIntent / $ref
      Previous value: -"#/properties/settings/properties/jevFeatures/properties/replyIntent"New value: +"#/properties/settings/properties/jevFeatures/properties/confidenceGate"
    • removedInput schema / properties / settings / properties / jevFeatures / properties / confidenceGate / $ref
      Removed value: -"#/properties/settings/properties/jevFeatures/properties/replyIntent"
    • addedInput schema / properties / settings / properties / jevFeatures / properties / confidenceGate / enum
      Added value: +[
+  "off",
+  "shadow",
+  "live"
+]
    • addedInput schema / properties / settings / properties / jevFeatures / properties / confidenceGate / type
      Added value: +"string"
    • removedInput schema / properties / settings / properties / jevFeatures / properties / critic
      Removed value: -{
-  "$ref": "#/properties/settings/properties/jevFeatures/properties/replyIntent"
-}
    • changedInput schema / properties / settings / properties / jevFeatures / properties / draftLabels / $ref
      Previous value: -"#/properties/settings/properties/jevFeatures/properties/replyIntent"New value: +"#/properties/settings/properties/jevFeatures/properties/confidenceGate"
    • addedInput schema / properties / settings / properties / jevFeatures / properties / memoryMatch
      Added value: +{
+  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
+}
    • addedInput schema / properties / settings / properties / jevFeatures / properties / profileMatch
      Added value: +{
+  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
+}
    • removedInput schema / properties / settings / properties / jevFeatures / properties / replyIntent
      Removed value: -{
-  "enum": [
-    "off",
-    "shadow",
-    "live"
-  ],
-  "type": "string"
-}
    • addedInput schema / properties / settings / properties / jevFeatures / properties / replyRank
      Added value: +{
+  "$ref": "#/properties/settings/properties/jevFeatures/properties/confidenceGate"
+}
  4. 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."
  5. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already establish a non-destructive, non-read-only, non-idempotent write. The description adds real behavioral context beyond them: partial-update semantics ('Only supplied components change'), the blast radius of branding (client-facing shared artifacts only), what compliance toggles, and that restores are versioned. It omits permissions/auth requirements and reversibility details.

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 operation list is front-loaded in the first sentence, followed by the partial-update rule and per-component effects, ending with the cross-tool instruction. Dense but every sentence carries information; minor compression is possible.

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 multi-purpose mutation with an output schema present, the description covers operation scope, partial-update behavior, per-component effects, and prerequisites for the proposal decision. It is complete enough to call correctly, with only permission/reversibility details left unaddressed.

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?

Top-level schema coverage is low (17%), but the nested schemas carry deep inline documentation (sections, companyProfile, outreachIntents). The description adds meaning by mapping components to effects (branding, compliance toggle, versioned restore, proposal decision) but supplies no syntax, format, or required-combination detail, so it only partially compensates.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates the concrete operations (write settings, branding, compliance, restore a playbook version, accept/reject a proposal) on the workspace resource, so an agent knows exactly what it does. It implicitly distinguishes from siblings like edit_workspace_accounts or edit_workspace_members by limiting scope to settings/branding/compliance/playbook, though it does not name those siblings explicitly.

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 a clear routing instruction for the proposal case: read the pending proposal via campaignstack_get_workspaces' playbookProposal include before deciding. It also states the optimistic-update rule ('Only supplied components change'). It lacks explicit when-not guidance for the settings/branding/compliance operations.

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