neuron

Create List Campaign

neuron_create_list_campaign

Create a paced campaign that messages the next N un-reached members of a contact list on a schedule. The cursor follows the LIVE list — as members are added or removed, only current members get reached, and nobody is messaged twice per cycle. Multiple campaigns can run on the same or different lists concurrently. On exhaust, either stop or loop (start over after a cooldown).

Input Schema

TableJSON Schema

Name	Required	Description
`name`	No	Campaign name (default: 'Campaign')
`botId`	No	Bot to send through when sendMode='bot'; its channel is used
`listId`	Yes	The contact list to run the campaign over
`schedule`	Yes	When each batch fires. e.g. daily at 9am in Africa/Lagos, or every weekend.
`sendMode`	No	'message' sends a plain broadcast; 'bot' initiates the conversation through a bot (default: 'message')
`batchSize`	No	How many contacts to message per run (default: 20)
`channelId`	No	WhatsApp channel to send from; falls back to the org default / first connected channel
`onExhaust`	No	When the whole list has been reached: 'stop' (default) completes the campaign; 'loop' starts a new cycle after loopCooldownMs
`messageSource`	Yes	How the message is resolved live at each batch run: 'static' (fixed), 'rotation' (cycle through several), 'ai' (AI-written), 'webhook' (from your service), or 'content' (a saved Neuron Note).
`loopCooldownMs`	No	Milliseconds to wait before looping (default: 24h)
`startImmediately`	No	Fire the first batch right away (default: true). Set false to wait for the first scheduled slot

TDQS

A4.6/5.0

Behavior5/5

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

The annotations only give false flags, so the description carries the burden. It discloses key behavioral traits: the cursor follows the live list, members are only messaged once per cycle, multiple campaigns can run concurrently, and exhaust can stop or loop. These beyond-annotation details are essential for predicting side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Four sentences, each earning its place: purpose, cursor behavior, concurrency, and exhaust handling. The action verb 'Create' is front-loaded, with no filler or repetition of schema details.

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 a complex 11-parameter create tool with no output schema, the description covers the core operational semantics (live cursor, pacing, concurrency, exhaust) while the schema handles field-level detail. It doesn't mention prerequisites or auth, but those are not critical for this create operation given the rich 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 description coverage is 100% (baseline 3), and the description adds semantic glue: 'next N' maps to batchSize, 'on exhaust' to onExhaust, and 'cursor follows the LIVE list' clarifies the behavior of listId over time. This enriches parameter understanding beyond the individual 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 opens with 'Create a paced campaign that messages the next N un-reached members of a contact list on a schedule,' which is a specific verb+resource statement. The live-cursor and cycle behaviors further distinguish it from generic campaign or broadcast tools like create_broadcast or create_campaign.

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?

It provides clear context: use for paced campaigns over a contact list, with concurrency and stop/loop behavior explained. However, it does not explicitly name alternatives or state when not to use it (e.g., versus create_broadcast for one-off sends), so it falls short of a 5.

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

All neuron tools Inspect

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

B3.4/5.0

Disambiguation3/5

Most tools are clearly separated by resource type, but there is meaningful overlap in messaging entry points (send_message, send_whatsapp, compose_message, bot_api_send) and contact ingestion/sync tools (import_contacts, populate_contacts, sync_whatsapp_contacts). The descriptions help disambiguate, but with 309 tools an agent will frequently need to read closely to pick the right one.

Naming Consistency4/5

The overwhelming majority of tools follow a consistent verb_noun snake_case pattern: create_*, get_*, list_*, update_*, delete_*. Minor deviations like sales_stats, lead_stats, wallet_balance, and whoami break the pattern slightly, but overall naming is highly predictable.

Tool Count1/5

309 tools is an extreme count for any MCP server, even a broad platform. This creates significant cognitive load and navigation overhead for agents, and far exceeds the well-scoped 3-15 tool range where coherence is strongest.

Completeness4/5

The tool surface is remarkably comprehensive across bots, contacts, campaigns, flows, knowledge bases, personas, marketplace, wallet, and products. Minor gaps exist — lead sources lack update/delete tools, and there is no single get_task or get_webhook alongside their list/update/delete counterparts — but these are workable gaps rather than dead ends.

Resources

Need Help?