Sendocado

Create broadcast

create_broadcast

Create a broadcast as a draft: one email to everyone the audience matches, sent once. Nothing sends while it is a draft. Preview the audience (preview_audience), send a test (send_test_email) and show the user before set_broadcast_status.

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": {
      "project_id": "<project_id>",
      "name": "<name>",
      "filter_groups": "<filter_groups>",
      "subject": "<subject>",
      "preview_text": "<preview_text>",
      "html": "<html>",
      "markdown": "<markdown>",
      "template_id": "<template_id>"
    },
    "name": "create_broadcast"
  }
}

Input Schema

Name	Required	Description
`html`	Yes	The body as HTML. Null when you send markdown or a template_id.
`name`	Yes
`subject`	Yes
`markdown`	Yes	The body as markdown. Null when you send html or a template_id.
`project_id`	Yes
`template_id`	Yes	Copy a template's subject, preview text and body; then subject, preview_text, html and markdown are null.
`preview_text`	Yes	The line inbox previews show after the subject.
`filter_groups`	Yes	A contact matches when it passes every filter of at least one group. An empty list means every contact in the project.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, but the description adds the important behavioral fact that nothing is sent while in draft — creation is not the send. It does not warn that repeated calls create duplicate drafts (relevant given idempotentHint=false) or mention permission/sender or domain prerequisites.

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?

Three tight sentences with no filler: identity of the resource first, the no-send guarantee second, the verification workflow third. Every sentence carries distinct information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For an 8-required-parameter write tool with a nested filter_groups structure and no output schema, the description covers workflow but not how to fill the body/subject/template fields or what the call returns. Without a stated return value, the agent cannot tell whether it gets an identifier needed for the follow-on set_broadcast_status call.

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?

Schema coverage is 63%, above the point where the schema carries most of the burden, and the description adds no parameter-level meaning at all. Notably the mutual exclusivity between html, markdown and template_id is only implied in individual field descriptions, not stated as a rule the agent must satisfy.

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 and resource ("Create a broadcast as a draft") and immediately disambiguates what a broadcast is: one email to a matched audience, sent once. That contrast implicitly separates it from the campaign siblings (create_campaign, draft_campaign) without needing the 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?

It lays out the intended workflow explicitly: create the draft, verify with preview_audience, send_test_email, show the user, then set_broadcast_status. That is concrete next-step guidance naming real siblings. It stops short of stating when NOT to use this tool (e.g., single transactional sends via send_transactional_email, or multi-step sequences via create_campaign).

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

All Sendocado 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?