Send4

Create a campaign draft

create_campaign

Destructive

Create a campaign as a draft: which active flow it sends, from which number or mailbox, and to whom: leads by id, everyone with some tags, a pasted list, or the people of an earlier campaign (copy_from_campaign_id with copy_scope). Nothing is sent. An email campaign needs a subject. A goal is any card outcome of the flow except failed, with an optional target; without one it uses the flow's booking, if it books.

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": {
      "name": "<name>",
      "flow_id": "<flow_id>",
      "channel_id": "<channel_id>"
    },
    "name": "create_campaign"
  }
}

Input Schema

Name	Required	Description
`goal`	No	`card_id` and `outcome` from `read_flow`, optional `target`.
`name`	Yes	Shown on the Campaigns page.
`flow_id`	Yes	An active flow with a campaign trigger.
`subject`	No	Email only: the first email's subject.
`tag_ids`	No	Up to 10.
`lead_ids`	No	From `list_leads`.
`tag_match`	No	With several tags: leads with `any` (default) or `all` of them.
`channel_id`	Yes	The number or mailbox it sends from, from `list_channels`.
`copy_scope`	No	Who of that campaign: everyone, those not reached, or those who never replied.
`pasted_recipients`	No	One recipient per line.
`copy_from_campaign_id`	No	Run a finished campaign again. Not with lead_ids or pasted_recipients.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedNov 6, 2026

addedInput schema / properties / channel_id / description

Added value: +"The number or mailbox it sends from, from `list_channels`."

addedInput schema / properties / copy_scope / description

Added value: +"Who of that campaign: everyone, those not reached, or those who never replied."

addedInput schema / properties / goal / description

Added value: +"`card_id` and `outcome` from `read_flow`, optional `target`."

addedInput schema / properties / lead_ids / description
```
Added value: +"From `list_leads`."
```
addedInput schema / properties / name / description
```
Added value: +"Shown on the Campaigns page."
```

addedInput schema / properties / subject / description

Added value: +"Email only: the first email's subject."

addedInput schema / properties / tag_match / description

Added value: +"With several tags: leads with `any` (default) or `all` of them."

First observedNov 5, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false; the description adds the key behavioral fact that nothing is sent and that the result is a draft, plus the mutual-exclusion rule for copy_from_campaign_id. It does not explain what the draft creation returns or whether repeated calls create duplicates, which is the main remaining gap for a non-idempotent write.

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 action and recipient modes, then conditional rules. Dense but every clause carries information; the nested parentheticals and colon-heavy phrasing make it slightly harder to scan than it could be.

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 an 11-parameter, nested-object write tool with no output schema, the description covers recipient selection, goal semantics, email subject requirement, and copy constraints. It omits what the call returns (e.g., a campaign id for later launch) and any validation limits beyond those in the schema.

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 100%, so the baseline is 3, but the description genuinely adds meaning: goal is any card outcome except failed with an optional target defaulting to the flow's booking, and copy_scope defines who is copied. These semantics go beyond the field-level schema text.

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 ('Create a campaign as a draft') and immediately enumerates the recipient modes (lead ids, tags, pasted list, copy from earlier campaign), which cleanly separates it from launch_campaign, update_campaign, and add_campaign_recipients. An agent can identify the tool without opening 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?

Gives clear conditional rules: 'Nothing is sent' (draft, not launch), an email campaign needs a subject, and copy_from_campaign_id cannot be combined with lead_ids or pasted_recipients. It stops short of naming the sibling to use for sending (launch_campaign) or for audience checking (preview_campaign_audience), so routing is implied rather than explicit.

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

All Send4 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.