Skip to main content
Glama

Create broadcast draft

createBroadcastDraft

Save a send to audiences as a draft, without sending it. Nothing goes out and nothing counts against the plan. updateBroadcast changes it, sendBroadcastTest sends a test copy, and sendBroadcastDraft sends or schedules it. Takes the same fields as sendToAudience, but audienceIds may be left out until later. Each person gets their own copy, so nobody sees anybody else. Personalise with {{firstName}}, {{lastName}}, {{name}}, {{email}} and {{unsubscribeUrl}}, and give a fallback after a bar: {{firstName|there}}. A custom field of the contact is {{attributes.}} in the subject and an html or text body, such as {{attributes.plan|Free}}, and reads as its fallback, or nothing, when the contact has no such field. Every copy carries a one-click unsubscribe header, and a short unsubscribe line is added at the end of an html or text body that does not place {{unsubscribeUrl}} itself. A template gets the same values as props, for the props it declares.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "from": "<from>"
    },
    "name": "createBroadcastDraft"
  }
}

Input Schema

NameRequiredDescriptionDefault
utmNoCampaign tags added to the links, such as { source, medium, campaign }.
fromYes
htmlNo
tagsNoUp to 8 tags of your own, copied onto every copy beside broadcast_id.
textNo
propsNo
slotsNoValues for the template's slots, the parts its layout leaves for each send.
abTestNoAn A/B test: 2 to 4 variants, each a subject or a body (html or text) that replaces the broadcast's own ({} keeps it), testPercent of the people (5 to 50, 20 unless set) split evenly between them, metric (opens or clicks) to pick the winner, and waitMinutes (30 to 4320, 240 unless set) to wait before picking it. Everybody else then gets the winning variant. A template broadcast can only vary the subject.
replyToNo
subjectNo
segmentIdNoA saved segment id (seg_...) that narrows the audiences: only the contacts that match its conditions get a copy. listSegments shows them.
templateIdNo
trackOpensNo
audienceIdsNo
trackClicksNo
templateVersionNo
excludeAudienceIdsNoAudiences whose members are left out, even when they are in one of audienceIds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations give the safety profile (readOnly=false, destructive=false, openWorld=false), and the description adds real context beyond that: nothing is delivered and nothing counts against the plan, each recipient gets an isolated copy, an unsubscribe header is forced on and a line is appended when {{unsubscribeUrl}} is absent. It does not cover whether a partially specified draft is valid (e.g. no html/text/templateId) or what a template-bound draft rejects, which is the remaining behavioral gap.

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?

Front-loaded with the core distinction and the sibling routing, which is the right ordering. The personalisation and unsubscribe material is dense but earns its place; the trailing template/props sentence is slightly cryptic and could be tighter.

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 17-parameter, nested-object create tool with no output schema, the description covers the non-obvious semantics (deferred audiences, template props, placeholder grammar, forced unsubscribe). What remains unstated is what an agent gets back — presumably a draft id needed for the follow-up sendBroadcastDraft call — and the minimum content requirement to create a valid draft.

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 only 35% across 17 parameters, so the description has to compensate and largely does for the ambiguous ones: audienceIds is optional until later, subject/html/text personalisation syntax with fallbacks, {{attributes.<key>}} custom fields, and props being fed to a template's declared props. It says nothing about the utm/tags/slots/abTest/segmentId/excludeAudienceIds relationships, though those carry their own 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?

States a specific verb and resource ('Save a send to audiences as a draft') plus the defining constraint ('without sending it'). It then explicitly separates itself from four siblings — updateBroadcast, sendBroadcastTest, sendBroadcastDraft, sendToAudience — so an agent can pick it out of a ~250-tool namespace without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Names the alternatives and the condition that selects each: updateBroadcast to change, sendBroadcastTest for a test copy, sendBroadcastDraft to send or schedule. It also states the relationship to sendToAudience (same fields, but audienceIds can be deferred), which is exactly the routing information an agent needs.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.