Skip to main content
Glama

xmagnet

by ai.xmagnet.api
OverviewDiscussionsAdmin

create_campaign

Create a DRAFT email campaign via a programmatic wizard. Call this tool and it will guide through the steps — no manual orchestration needed. WIZARD STEPS (handled automatically by the tool):

  1. Call with contacts + total_contacts → tool returns engine picker (NextGen vs MyConvo)

  2. Add campaign_type from user's click → tool returns campaign category chips (promotional, newsletter, event…)

  3. Add campaign_category from user's click → tool returns engine-specific template gallery MyConvo: shows plain_email_templates (personal plain-text). NextGen: shows campaign_templates (HTML).

  4. Add template_id from user's pick → tool creates the draft campaign. RULES: Reuse contacts from prior search — never re-search. Pass total_contacts from search result's total_in_crm so the user always sees the full count. Saves as DRAFT only — no emails sent.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyNoEmail body (only needed for AI-generate path, not template path).
nameYesCampaign name
toneNoEmail tone — collected from user alongside campaign_description.
subjectNoSubject line (only needed for AI-generate path, not template path).
contactsNoContact objects from prior search to add as recipients.
template_idNoTemplate ID selected by user from wizard step 3 gallery.
from_accountNoSender email address (MyConvo only).
campaign_typeNoEngine chosen by user. Omit on first call — tool will prompt.
total_contactsNoTotal contact count from search result's total_in_crm. Always pass this so user sees full count.
campaign_categoryNoCampaign category chosen by user. Omit until user picks from wizard step 2.
campaign_descriptionNoWhat the campaign is about — collected from user when no MyConvo templates found. Used to auto-generate plain-text content.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed11 schema fields changed
    • addedInput schema / properties / body
      Added value: +{
+  "description": "Email body (only needed for AI-generate path, not template path).",
+  "type": "string"
+}
    • addedInput schema / properties / campaign_category
      Added value: +{
+  "description": "Campaign category chosen by user. Omit until user picks from wizard step 2.",
+  "enum": [
+    "promotional",
+    "newsletter",
+    "event",
+    "lead_gen",
+    "follow_up",
+    "product"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / campaign_description
      Added value: +{
+  "description": "What the campaign is about — collected from user when no MyConvo templates found. Used to auto-generate plain-text content.",
+  "type": "string"
+}
    • changedInput schema / properties / campaign_type / description
      Previous value: -"Must be explicitly chosen by user — never default"New value: +"Engine chosen by user. Omit on first call — tool will prompt."
    • changedInput schema / properties / contacts / description
      Previous value: -"Contact objects to add as recipients"New value: +"Contact objects from prior search to add as recipients."
    • changedInput schema / properties / from_account / description
      Previous value: -"Sender email address (MyConvo only)"New value: +"Sender email address (MyConvo only)."
    • addedInput schema / properties / subject
      Added value: +{
+  "description": "Subject line (only needed for AI-generate path, not template path).",
+  "type": "string"
+}
    • changedInput schema / properties / template_id / description
      Previous value: -"REQUIRED. Template ID from list_campaign_templates. Always call list_campaign_templates first and let user pick."New value: +"Template ID selected by user from wizard step 3 gallery."
    • addedInput schema / properties / tone
      Added value: +{
+  "description": "Email tone — collected from user alongside campaign_description.",
+  "enum": [
+    "professional",
+    "friendly",
+    "casual",
+    "urgent"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / total_contacts
      Added value: +{
+  "description": "Total contact count from search result's total_in_crm. Always pass this so user sees full count.",
+  "type": "integer"
+}
    • changedInput schema / required
      Previous value: -[
-  "name",
-  "campaign_type",
-  "template_id"
-]New value: +[
+  "name"
+]
  2. Changed8 schema fields changed
    • removedInput schema / properties / body
      Removed value: -{
-  "description": "Email body (HTML or plain text)",
-  "type": "string"
-}
    • removedInput schema / properties / campaign_type / default
      Removed value: -"myconvo"
    • addedInput schema / properties / campaign_type / description
      Added value: +"Must be explicitly chosen by user — never default"
    • changedInput schema / properties / contacts / description
      Previous value: -"List of contact objects to add as recipients"New value: +"Contact objects to add as recipients"
    • changedInput schema / properties / from_account / description
      Previous value: -"Sender email address"New value: +"Sender email address (MyConvo only)"
    • removedInput schema / properties / subject
      Removed value: -{
-  "description": "Email subject line",
-  "type": "string"
-}
    • addedInput schema / properties / template_id
      Added value: +{
+  "description": "REQUIRED. Template ID from list_campaign_templates. Always call list_campaign_templates first and let user pick.",
+  "type": "integer"
+}
    • changedInput schema / required
      Previous value: -[
-  "name",
-  "subject",
-  "body"
-]New value: +[
+  "name",
+  "campaign_type",
+  "template_id"
+]
  3. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only indicate not read-only and not destructive. The description adds substantial behavioral detail: it is a multi-step wizard with intermediate returns (engine picker, category chips, template gallery), saves as DRAFT only, and sends no emails. This goes well beyond the annotation basics.

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 front-loaded with the purpose and then structured into clearly labeled 'WIZARD STEPS' and 'RULES.' Every sentence earns its place, providing necessary context without filler.

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?

Even without an output schema, the description covers the tool's full behavior: intermediate picks and their order, the final draft creation, and rules for contact reuse. Given the 11-parameter, multi-step complexity, this is a complete and self-sufficient description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although schema coverage is 100%, the description adds critical semantics: which parameters to pass at each wizard step (e.g., omit campaign_type until prompted), body/subject only for the AI-generate path, and total_contacts sourced from total_in_crm. This meaningfully elevates the parameter understanding beyond schema descriptions.

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 clearly states 'Create a DRAFT email campaign via a programmatic wizard,' using a specific verb and resource. It distinguishes itself from siblings like create_sequence_draft by focusing on campaigns and the draft state.

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 provides explicit wizard steps and rules, such as 'Reuse contacts from prior search — never re-search' and 'Pass total_contacts from search result's total_in_crm.' While it doesn't name alternative tools for exclusion, it offers clear contextual guidance for when and how to invoke this tool.

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

All xmagnet 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