Sendocado

Create campaign

create_campaign

Create a campaign as a draft: its audience, schedule and emails, sent in the order given with delay_days before each (the first counts from when a contact enters). Nothing sends while it is a draft. Show the user the result and the audience (preview_audience) before set_campaign_status live. Add branches afterwards with update_campaign_step. For activation emails, exclude the tag the user's app adds at finished setup, so people leave once they are set up.

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>",
      "timezone": "<timezone>",
      "send_window": "<send_window>",
      "is_stopped_on_reply": "<is_stopped_on_reply>",
      "filter_groups": "<filter_groups>",
      "steps": "<steps>"
    },
    "name": "create_campaign"
  }
}

Input Schema

Name	Required	Description
`name`	Yes
`steps`	Yes
`timezone`	Yes	IANA time zone the send window is read in, unless the contact has its own.
`project_id`	Yes
`send_window`	Yes	When emails may go out, in the contact's time zone (else the campaign's). Null sends at any hour.
`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.
`is_stopped_on_reply`	Yes	True ends a contact's campaign when they reply to any of its emails.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 5, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent and closed-world, so the description isn't carrying the safety burden. It still adds real behavior: the object is created as a draft with no sending, steps fire in the given order, and delay_days is measured before each step with the first counted from contact entry. It stops short of saying what happens on duplicate calls or what permissions are required.

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 first clause front-loads what is created and that it stays a draft; subsequent sentences each carry a distinct operational instruction. It is dense but nearly every sentence earns its place, with the activation-tag tip being the most tangential item.

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 a 7-required-parameter creation tool with a deeply nested steps/filter_groups schema and no output schema, the description conveys the lifecycle and the sequencing semantics well. However it never says what the call returns or how to reference the created campaign afterward (beyond "show the user the result"), and it leaves the send_window/timezone/stop-on-reply configuration unexplained.

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 description coverage is 57%, so the description partly compensates: it explains steps ordering and delay_days semantics, and hints that the audience is expressed through filter tags (the activation-tag exclusion rule). It says nothing about timezone, send_window, is_stopped_on_reply or name beyond what the schema already provides.

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?

"Create a campaign as a draft" is a specific verb+resource with the key qualifier that nothing sends until activation. It clearly distinguishes the tool from set_campaign_status and update_campaign_step. The only gap is that the sibling draft_campaign is never mentioned, so an agent cannot tell from the description how create_campaign differs from it.

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?

It prescribes a concrete workflow: show the user the result and preview_audience before calling set_campaign_status to go live, and use update_campaign_step for branches afterwards. It also gives a conditional rule for activation campaigns (exclude the tag the app adds at finished setup) so contacts exit once set up. This is explicit when-to-use and next-step guidance rather than implied usage.

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?