Vendo AI

Create a campaign (DRAFT, not launched)

create_campaign

Create a classic campaign in DRAFT — nobody is contacted until launch_campaign. Needs an audience (audienceId from save_audience/list_audiences, OR customAudienceId of a READY uploaded/CRM list) and should get an agentId (a campaign cannot be launched without an agent: AGENT_REQUIRED). branchId = CRM branch for replies (crm_list_branches; null = General). Settings (all optional): channels, dailyLimit, dailyEmailLimit, dailyLinkedinLimit, timezone, workingHours, excludeWeekends, campaignDurationDays, customInstructions (Communication Rules incl. form of address), emailSignature, notifyEmails, ccEmail, autoResponseEnabled, autoResponseDelayMinutes, followUpInterval, maxFollowUps, trackOpens, emailSenderMode (managed needs a paid plan), senderEmailIds, emailContent {mode, prompt, tone, variants, htmlSteps, followUps[{delayDays, prompt|subject+body}]}, linkedinContent {mode, invite_prompt, invite_tone, invite_exact_text, followup_delay_minutes, followup_exact_text}, selectedLinkedinAccountIds, linkedinAutoReplyDisabled. Ids are checked against the workspace. Free, no sending.

Input Schema

Name	Required	Description
`name`	Yes
`agentId`	No	Sales agent id (list_agents). Required before launch.
`branchId`	No	CRM branch id for replies; null = General
`settings`	No
`audienceId`	No	Campaign audience id
`description`	No
`customAudienceId`	No	Instead of audienceId: id of a READY custom audience (uploaded CSV/CRM list); an audience is created from it

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 27, 2026

changedInput schema / properties / settings / properties / workingHours / description

Previous value: -"[startHour, endHour] in the campaign timezone (default [9,18])."New value: +"[startHour, endHour] in the campaign timezone (default [9,18]). Two integers: start 0-23, end 1-24."

changedInput schema / properties / settings / properties / workingHours / items

Previous value: -[
-  {
-    "maximum": 23,
-    "minimum": 0,
-    "type": "integer"
-  },
-  {
-    "maximum": 24,
-    "minimum": 1,
-    "type": "integer"
-  }
-]New value: +{
+  "maximum": 24,
+  "minimum": 0,
+  "type": "integer"
+}

Changed7 schema fields changedOct 26, 2026

addedInput schema / properties / agentId / description

Added value: +"Sales agent id (list_agents). Required before launch."

addedInput schema / properties / audienceId / description
```
Added value: +"Campaign audience id"
```

addedInput schema / properties / branchId

Added value: +{
+  "description": "CRM branch id for replies; null = General",
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedInput schema / properties / customAudienceId

Added value: +{
+  "description": "Instead of audienceId: id of a READY custom audience (uploaded CSV/CRM list); an audience is created from it",
+  "type": "string"
+}

changedInput schema / properties / settings / additionalProperties
```
Previous value: -{}New value: +true
```

addedInput schema / properties / settings / properties

Added value: +{
+  "autoResponseDelayMinutes": {
+    "description": "Delay before the AI email auto-reply (default 10).",
+    "minimum": 0,
+    "type": "integer"
+  },
+  "autoResponseEnabled": {
+    "description": "AI answers email replies automatically (default true).",
+    "type": "boolean"
+  },
+  "campaignDurationDays": {
+    "description": "Planned duration in days (default 30).",
+    "minimum": 1,
+    "type": "integer"
+  },
+  "ccEmail": {
+    "description": "Address put in CC of outgoing emails.",
+    "type": "string"
+  },
+  "channels": {
+    "description": "Channels the campaign uses (default ['email']).",
+    "items": {
+      "enum": [
+        "email",
+        "linkedin",
+        "phone_call"
+      ],
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "clientEmailProvider": {
+    "anyOf": [
+      {
+        "enum": [
+          "google",
+          "microsoft"
+        ],
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ],
+    "description": "Informational provider of own mailboxes."
+  },
+  "customInstructions": {
+    "description": "Communication Rules: CTA, links, promises, what never to say. Overrides prompt defaults in emails, follow-ups, AI auto-replies and LinkedIn. Also sets the informal/formal form of address (e.g. ти/Ви, du/Sie) when the rules say so.",
+    "maxLength": 6000,
+    "type": "string"
+  },
+  "dailyEmailLimit": {
+    "description": "Emails per day; the app keeps it equal to dailyLimit.",
+    "minimum": 0,
+    "type": "integer"
+  },
+  "dailyLimit": {
+    "description": "New contacts emailed per day. Must not exceed sender capacity (list_sender_emails / list_client_mailboxes). Default 200.",
+    "minimum": 0,
+    "type": "integer"
+  },
+  "dailyLinkedinLimit": {
+    "description": "Campaign-wide LinkedIn invites per day across ALL its accounts (hard limit). Each account also has its own warm-up cap.",
+    "minimum": 0,
+    "type": "integer"
+  },
+  "emailContent": {
+    "additionalProperties": true,
+    "description": "Email content (wizard step 4). On a running campaign a change to steps/delays is NOT applied once anything was sent; see settings.smartleadSequencePending in get_campaign.",
+    "properties": {
+      "followUps": {
+        "description": "Follow-ups after the first email (max 7).",
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "body": {
+              "description": "Fixed mode: body.",
+              "maxLength": 20000,
+              "type": "string"
+            },
+            "delayDays": {
+              "description": "Days after the previous email.",
+              "maximum": 90,
+              "minimum": 1,
+              "type": "integer"
+            },
+            "prompt": {
+              "description": "AI mode: writing rules for this follow-up.",
+              "maxLength": 4000,
+              "type": "string"
+            },
+            "subject": {
+              "description": "Fixed mode: subject.",
+              "maxLength": 500,
+              "type": "string"
+            }
+          },
+          "required": [
+            "delayDays"
+          ],
+          "type": "object"
+        },
+        "maxItems": 7,
+        "type": "array"
+      },
+      "htmlSteps": {
+        "description": "HTML mode: one entry per email; delayDays = days after the previous email (not on the first).",
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "delayDays": {
+              "maximum": 90,
+              "minimum": 1,
+              "type": "integer"
+            },
+            "html": {
+              "type": "string"
+            },
+            "subject": {
+              "maxLength": 500,
+              "type": "string"
+            }
+          },
+          "required": [
+            "subject",
+            "html"
+          ],
+          "type": "object"
+        },
+        "maxItems": 20,
+        "type": "array"
+      },
+      "mode": {
+        "description": "ai = AI writes each email from the prompt; fixed = your text with {{first_name}}-style placeholders; html = your own HTML steps.",
+        "enum": [
+          "ai",
+          "fixed",
+          "html"
+        ],
+        "type": "string"
+      },
+      "prompt": {
+        "description": "AI writing rules for the first email.",
+        "type": "string"
+      },
+      "tone": {
+        "enum": [
+          "formal",
+          "casual",
+          "friendly"
+        ],
+        "type": "string"
+      },
+      "variants": {
+        "description": "Fixed mode: up to 5 A/B variants of the first email.",
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "body": {
+              "type": "string"
+            },
+            "subject": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "subject",
+            "body"
+          ],
+          "type": "object"
+        },
+        "maxItems": 5,
+        "type": "array"
+      }
+    },
+    "required": [
+      "mode"
+    ],
+    "type": "object"
+  },
+  "emailSenderMode": {
+    "description": "managed = Vendo warmed pool (PAID PLAN REQUIRED to launch); client_owned = the workspace's own mailboxes (connect_client_mailbox). Default managed.",
+    "enum": [
+      "managed",
+      "client_owned"
+    ],
+    "type": "string"
+  },
+  "emailSignature": {
+    "description": "HTML signature appended to emails ('' = no signature).",
+    "type": "string"
+  },
+  "excludeWeekends": {
+    "description": "Do not send on Saturday/Sunday (default true).",
+    "type": "boolean"
+  },
+  "followUpInterval": {
+    "description": "Legacy: days between follow-ups, used only when emailContent.followUps is empty (default 3).",
+    "minimum": 0,
+    "type": "integer"
+  },
+  "linkedinAutoReplyDisabled": {
+    "description": "Switch LinkedIn AI auto-replies OFF for this campaign only (per-account settings: update_linkedin_account_settings).",
+    "type": "boolean"
+  },
+  "linkedinContent": {
+    "additionalProperties": true,
+    "description": "LinkedIn content (wizard step 5).",
+    "properties": {
+      "followup_delay_minutes": {
+        "description": "Delay of the first message after the invite is accepted.",
+        "maximum": 43200,
+        "minimum": 0,
+        "type": "integer"
+      },
+      "followup_exact_text": {
+        "description": "Fixed first message after connect.",
+        "maxLength": 1500,
+        "type": "string"
+      },
+      "invite_exact_text": {
+        "description": "Fixed connection note (LinkedIn sends max 200 chars).",
+        "maxLength": 300,
+        "type": "string"
+      },
+      "invite_prompt": {
+        "description": "AI rules for the connection note (also used for the form of address).",
+        "type": "string"
+      },
+      "invite_tone": {
+        "$ref": "#/properties/settings/properties/emailContent/properties/tone"
+      },
+      "mode": {
+        "enum": [
+          "ai",
+          "fixed"
+        ],
+        "type": "string"
+      }
+    },
+    "required": [
+      "mode"
+    ],
+    "type": "object"
+  },
+  "maxFollowUps": {
+    "description": "Legacy: number of follow-ups when emailContent.followUps is empty (default 3).",
+    "maximum": 7,
+    "minimum": 0,
+    "type": "integer"
+  },
+  "notifyEmails": {
+    "description": "Addresses notified when a lead replies.",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "selectedLinkedinAccountIds": {
+    "description": "LinkedIn accounts used by this campaign (ids from list_linkedin_accounts). Empty = all connected accounts at launch.",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "senderEmailIds": {
+    "description": "Restrict sending to these sender ids from list_sender_emails (empty = auto-assign at launch).",
+    "items": {
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "speedTier": {
+    "enum": [
+      "conservative",
+      "balanced",
+      "aggressive"
+    ],
+    "type": "string"
+  },
+  "stopOnNegative": {
+    "description": "Saved like the app (currently not read by the sender).",
+    "type": "boolean"
+  },
+  "timezone": {
+    "description": "IANA timezone of the sending window, e.g. Europe/London (default).",
+    "type": "string"
+  },
+  "trackLinks": {
+    "description": "Saved like the app (currently not read by the sender).",
+    "type": "boolean"
+  },
+  "trackOpens": {
+    "description": "Insert the open-tracking pixel.",
+    "type": "boolean"
+  },
+  "workingHours": {
+    "description": "[startHour, endHour] in the campaign timezone (default [9,18]).",
+    "items": [
+      {
+        "maximum": 23,
+        "minimum": 0,
+        "type": "integer"
+      },
+      {
+        "maximum": 24,
+        "minimum": 1,
+        "type": "integer"
+      }
+    ],
+    "maxItems": 2,
+    "minItems": 2,
+    "type": "array"
+  }
+}

changedInput schema / required

Previous value: -[
-  "name",
-  "audienceId"
-]New value: +[
+  "name"
+]

First observedJul 28, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses that nothing is contacted until launch_campaign, that the operation is free (no credit spend), that ids are validated against the workspace, and that managed emailSenderMode requires a paid plan. It omits permissions requirements and what the response contains (e.g. the new campaign id), so not a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The critical facts (DRAFT, audience, agentId, branchId) are correctly front-loaded. However, the trailing run-on enumeration of thirty-plus setting names duplicates the schema and inflates the description without adding meaning, diluting the useful signal.

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 tool with nested objects, no output schema and moderate schema coverage, the description covers the hard prerequisites, the draft safety semantics and the cost profile. The main remaining gap is that it does not say what is returned or what to call next with the created id, though the DRAFT/launch framing implies it.

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?

At 57% schema coverage the description partially compensates, and it does clarify the audienceId vs customAudienceId choice and that settings are all optional. But its long settings enumeration largely restates field names already documented in the schema, and several parameters (speedTier, trackLinks, stopOnNegative, clientEmailProvider) are never mentioned at all.

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?

States a specific verb and resource plus the resulting lifecycle state ("Create a classic campaign in DRAFT") and immediately distinguishes it from launch_campaign. An agent can tell this is the creation step, not the activation step, without opening any schema.

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?

Gives explicit prerequisites: an audience via audienceId (from save_audience/list_audiences) OR customAudienceId of a READY list, an agentId, and branchId from crm_list_branches. It also names the AGENT_REQUIRED failure mode if agentId is skipped. It does not contrast with update_campaign for the modify case, but the create-then-launch flow is unambiguous.

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

All Vendo AI 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?