Skip to main content
Glama

Courier

by io.github.trycourier

create_journey

Create a new journey. Always created as a draft; making it live is a separate step this tool cannot perform. Send two nodes: the trigger, and an exit node last. Both are required — a create with no exit node is rejected, and the API reports that as "exit node must be the last node in the journey" even when no exit was sent at all. Send and delay nodes are added afterwards by replace_journey, once journey-scoped templates exist. Node ids are server-generated; do NOT include an id field. Example: { name: "Welcome Journey", nodes: [{ type: "trigger", trigger_type: "api-invoke" }, { type: "exit" }], enabled: true }. The result carries a "verification" object read back from the server after the write — check it every time. verified:true means what you asked for is what saved. verified:false names what did not: "fieldMismatches" for node fields that failed to land, "nodeCountMismatch" for a node dropped or added, and "unknownTemplateReferences" for a send node pointing at a template id this journey does not have — almost always a mistyped id, so re-copy it from the create_journey_template or get_journey response it came from. Fix the specific thing named and send the corrected document. Re-sending an identical call changes nothing, and every replace_journey overwrites the whole draft again. An "errorKind" of "unauthorized" means the write itself succeeded and only the read-back was refused: report that as unconfirmed, never as a failed write.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesJourney display name
nodesYesThe trigger node, then a terminal exit node — both required. Send and delay nodes are added later by replace_journey. Node ids are server-generated — do NOT include an id field. Example: [{ type: "trigger", trigger_type: "api-invoke" }, { type: "exit" }].
stateNoMust be "DRAFT". These tools cannot publish.
enabledNoWhether the journey is active. Defaults to true.

TDQS

A3.9/5.0
Behavior1/5

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

The description says "Re-sending an identical call changes nothing," implying idempotent behavior, but the annotations set idempotentHint to false. This is a direct contradiction on a critical behavioral property, so the description cannot be trusted as transparent.

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 long but information-dense; nearly every sentence adds operational detail or error-handling context. It is well front-loaded with the core draft-only and node-order rules, though the verification paragraph is verbose enough that it could be tightened.

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?

With no output schema, the description does a strong job explaining the verification object, mismatch categories, unauthorized errorKind handling, and the relationship to replace_journey. However, the conflict between the stated idempotence and idempotentHint:false leaves an unresolved, operationally important inconsistency.

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. The description still adds meaning beyond the schema: nodes must be trigger then exit, exit is required even though only name and nodes are in the schema's required list, node ids are server-generated and must be omitted, and verification failure modes map to specific node/template parameters.

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 "Create a new journey," naming a clear verb and resource, then sharpens scope with "Always created as a draft; making it live is a separate step this tool cannot perform." It distinguishes itself from replace_journey by noting send/delay nodes are added there, so an agent can separate create from modify.

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?

The description explicitly states when to use this tool versus replace_journey: send and delay nodes are added later by replace_journey once journey-scoped templates exist, and publishing is a separate step. It also gives corrective guidance for failed verification: fix only the named mismatch and resend.

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

All Courier toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0
Disambiguation3/5

Tools are mostly organized as distinct resource/action pairs, but several clusters are easy to confuse: list subscription tools (add_subscribers_to_list vs bulk_subscribe_to_list vs subscribe_user_to_list), message vs message-content vs message-history retrieval, and the many journey/journey-template list/get tools. Detailed descriptions rescue most selections, but the sheer number of near-identical verb/resource names creates real misselection risk.

Naming Consistency4/5

Almost all tools follow a snake_case verb_noun pattern (create_, get_, list_, replace_, send_, publish_, archive_). Minor deviations keep it from a perfect score: courier_installation_guide is noun-first, and add_bulk_users sits awkwardly next to the bulk_add_* family, but the overall convention is predictable and readable.

Tool Count1/5

144 tools is an extreme working-set size for an agent to hold and choose from, far beyond the reasonable 3–15 range. Even for a broad platform like Courier, this should be split into focused sub-servers (templates, journeys, users, lists, preferences, etc.) to remain usable.

Completeness4/5

The surface is remarkably comprehensive, covering sending, templates, journeys, automations, users, tenants, lists, preferences, providers, routing, brands, audiences, translations, digests, bulk jobs, and audit events. Notable gaps exist—automation template CRUD and digest schedule management are missing—but most workflows can still be completed with workarounds.

Resources