Create a preference section in your workspace. The section id is generated and returned. Add topics afterwards with create_preference_topic.
| Name | Required | Description | Default |
|---|---|---|---|
| name | Yes | Human-readable name for the section | |
| routing_options | No | Default channels for the section. Defaults to empty if omitted. | |
| has_custom_routing | No | Whether the section defines custom routing for its topics |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description discloses a concrete behavioral detail beyond the annotations: the section id is generated and returned. It also scopes the operation to 'your workspace.' The annotations already signal the mutation profile, so the description adds useful output-behavior context without needing to repeat safety hints.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two short sentences with no filler. The action and resource come first, followed by the key output behavior and a pointer to the relevant sibling tool. Every sentence earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a straightforward create tool with three well-documented parameters, the description covers the essential action, the returned id, and the next step in the workflow. It does not describe the full response shape or compare against replace_preference_section, but the id mention partially compensates for the missing output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the parameters name, routing_options, and has_custom_routing are already fully documented in the schema. The description adds no parameter-level meaning of its own, which lands it at the baseline 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description names a specific action and resource: creating a preference section. It also differentiates itself from the sibling create_preference_topic by explicitly pointing topic creation to that tool, and the note that the section id is generated and returned further clarifies the tool's purpose.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives clear workflow context by instructing the agent to add topics afterwards with create_preference_topic, which implies this tool is only for creating the section itself. It does not enumerate alternatives like replace_preference_section, but the creation-focused verb and the follow-up pointer provide sufficient orientation.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
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.
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.
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.
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.
