3Dsellers

create-automation

Create a standing automation — a trigger plus one or more actions that run every time it fires (scheduled price ladders, tag rules, auto end-and-relist). Created INACTIVE unless isActive is true, so you can read it back and check it before it touches live listings. Call get-automation-catalog first for the valid app / trigger / action combinations. Authenticated via bearer token.

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": {
      "app": "<app>",
      "name": "<name>",
      "trigger": "<trigger>",
      "actions": "<actions>"
    },
    "name": "create-automation"
  }
}

Input Schema

Name	Required	Description
`app`	Yes	Which app the automation belongs to
`name`	Yes	Automation name
`notes`	No	Free-text note
`actions`	Yes	Actions to perform when it fires
`channel`	No	Channel to limit to, or all_channels. Defaults to ebay.
`filters`	No	Optional filter tree narrowing which records the automation applies to — the same shape create-action takes and get-segments returns
`trigger`	Yes	Event that fires the automation, e.g. schedule, item_listed, Completed
`isActive`	No	Start it running immediately. Defaults to false.
`sellerId`	No	Limit to one seller account; omit for every account on the channel
`actionConfig`	No	Action-specific settings. Call get-automation-catalog for the keys each action reads. Must include a `schedule` object when trigger is "schedule".
`actionDelayMinutes`	No	Minutes to wait after the trigger before acting

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 26, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Adds substantial context beyond the annotations: the safe-by-default inactive state, the read-back verification pattern, the get-automation-catalog prerequisite, and the bearer-token auth requirement. The annotation set only says it is a non-read, non-destructive, closed-world call; the description supplies the operational behavior an agent actually needs.

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?

Three tight sentences with zero waste: the definition comes first, then the safety-relevant default, then the prerequisite. Each sentence earns its place and the most decision-critical information is front-loaded.

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 tool with nested objects and no output schema, the description covers the safe-default behavior, the catalog prerequisite, and auth. It doesn't say what the create call returns (e.g. the created automation with its id, which an agent would need for follow-up get-automation/update-automation calls), which is the one remaining gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter is already documented, including the isActive default and the actionConfig schedule requirement. The description largely restates those points rather than adding new semantics, so the baseline 3 is appropriate.

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 standing automation') and defines the resource structurally as 'a trigger plus one or more actions that run every time it fires'. Concrete examples (scheduled price ladders, tag rules, auto end-and-relist) make it easy to distinguish from single-action siblings like create-action.

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 real workflow guidance: defaults to INACTIVE so you can read it back and verify before it touches live listings, and explicitly says to call get-automation-catalog first for valid app/trigger/action combinations. It lacks an explicit 'when not to use this vs update-automation/create-action' statement, which keeps it 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 3Dsellers 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.