Courier

create_journey_template

Create a notification template scoped to a journey. Always created as a draft; making it live is a separate step this tool cannot perform. The template can then be referenced in journey send nodes. content.elements must be wrapped in a channel block — the API rejects bare elements. Example: { journey_id: "j-abc", channel: "email", notification: { name: "Welcome Email", tags: [], brand: null, subscription: null, content: { version: "2022-01-01", elements: [{ type: "channel", channel: "email", elements: [{ type: "text", content: "Hello!" }] }] } } }. The result carries a "verification" object confirming the new id is really present on the journey. verified:true means the id in this response is safe to reference from a send node. verified:false means it is not visible yet — re-read the journey before referencing it, and do not create a second template to work around it. An "errorKind" of "unauthorized" means the template was created and only the check was refused.

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": {
      "journey_id": "<journey_id>",
      "channel": "<channel>",
      "notification": "<notification>"
    },
    "name": "create_journey_template"
  }
}

Input Schema

Name	Required	Description
`state`	No	Must be "DRAFT". These tools cannot publish.
`channel`	Yes	Channel for this template (e.g. "email", "push", "sms", "inbox")
`journey_id`	Yes	The journey template ID. Copy it exactly, character for character, from the response that returned it — never retype it from memory or reconstruct it.
`notification`	Yes	Notification template definition
`provider_key`	No	Specific provider key to target

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 15, 2026

changedInput schema / properties / journey_id / description

Previous value: -"The journey template ID"New value: +"The journey template ID. Copy it exactly, character for character, from the response that returned it — never retype it from memory or reconstruct it."

changedInput schema / properties / notification / properties / content / properties / elements / description

Previous value: -"Elemental content nodes"New value: +"Elemental content nodes. Must be wrapped in a channel block — the API rejects bare elements. Example: [{ type: \"channel\", channel: \"email\", elements: [{ type: \"text\", content: \"Hello!\" }] }]."

Changed2 schema fields changedAug 19, 2026

changedInput schema / properties / state / description

Previous value: -"Initial state: \"DRAFT\" (default) or \"PUBLISHED\""New value: +"Must be \"DRAFT\". These tools cannot publish."

addedInput schema / properties / state / enum
```
Added value: +[
+  "DRAFT"
+]
```

AddedJun 7, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations only declare readOnlyHint false, but the description adds critical behavior: templates are always created as drafts, content.elements must be wrapped in a channel block or the API rejects it, the response carries a verification object whose semantics are explained, and an unauthorized errorKind still means the template was created. This goes far beyond the annotations and contains no contradictions.

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 description is longer than average, but every clause adds essential operational detail: draft status, channel block requirement, verification semantics, unauthorized caveat, and a complete example. It is front-loaded with the purpose before caveats. Slight redundancy with the schema's own examples keeps it from a 5.

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?

For a mutation tool with nested parameters and no output schema, the description covers the non-obvious behaviors an agent must know: creation always draft, verification result meaning, and errorKind semantics. Combined with 100% schema coverage and annotations, nothing critical is left to guesswork.

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?

Schema coverage is already 100%, but the description adds a complete example, explains the required nesting of elements inside a channel block, and warns to copy journey_id exactly rather than retype it. It also reinforces that state must be DRAFT. This adds meaning beyond the schema's field 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 states a specific verb and resource: 'Create a notification template scoped to a journey.' It immediately distinguishes this from siblings like create_notification (not journey-scoped) and create_journey (creates the journey, not the template). The draft-only constraint further clarifies what the tool does and does not do.

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 clearly frames when to use the tool: to create a journey-scoped notification template that is always a draft, and explicitly says making it live is a separate step this tool cannot perform, implicitly pointing to publish_journey_template. It also gives fallback guidance for verification false (re-read journey, do not create a second template). It does not name sibling tools explicitly, so not a 5.

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

All Courier 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.