Skip to main content
Glama
SunLicense MCP server

SunLicense MCP server

Official

create_automation

Save a new automation as an off draft with any problems listed, so nothing runs until switched on. Validate it before testing.

Instructions

Save a new automation. It is always saved switched off (a draft), with any problems listed, so nothing runs until the user switches it on. Check it with validate_automation first; afterwards test it with test_automation. Counts toward the plan's automations. A graph is {"nodes":[…],"edges":[…]}, a tree from exactly one trigger. Nodes: {"id","kind","type","config"}; kind is "trigger" (type: a trigger key, id "trigger"), "action" (type: an action key) or "condition" (no type; config {"cel": "<CEL expression over the trigger's fields>"}). Edges: {"from","to"} in the order nodes run; edges leaving a condition carry "branch": "true" (Yes) or "false" (No). Settings marked placeholders accept {{field.key}} from the trigger's fields, e.g. "{{license.id}}". CEL is typed: compare ints with ints (license.machinesUsed > 2), doubles with doubles (2.0), timestamps with timestamp("2026-01-01T00:00:00Z") or now ± duration("72h"); string fields with options only take those values.

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": {
      "name": "<name>",
      "graph": "<graph>"
    },
    "name": "create_automation"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYeswhat it does, e.g. 'Suspend shared licenses' (at most 80 characters)
graphYes
descriptionNoone or two sentences for the team (at most 500 characters)

Output Schema

NameRequiredDescriptionDefault
nextYeswhat to do next
automationYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations declare non-read-only, non-destructive, non-idempotent, closed-world, but say nothing about the draft lifecycle; the description adds that the automation is saved switched off and will not run until enabled, plus that problems are reported back. What remains vague is whether reported problems block the save or merely annotate the result, and whether repeat calls create duplicates given idempotentHint=false.

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?

Purpose, draft semantics, and the validate/test workflow are correctly front-loaded, and the graph grammar follows in logical order. The second half is a dense single-paragraph run of schema detail that would be easier to parse as a short list, but almost every clause carries information the agent cannot get elsewhere.

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 three-parameter tool with a deeply nested graph object, the definition covers the creation contract, the draft safety model, prerequisite and follow-up tools, and the full node/edge grammar. An output schema exists, so the absence of return-value documentation is not a gap.

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?

Well beyond the 67% schema coverage, the description defines the graph model itself: a tree from exactly one trigger, node shapes for trigger/action/condition, edge ordering, and the branch field on condition exits. It also supplies rules absent from the schema, such as typed CEL comparisons and {{field.key}} placeholders drawn from trigger fields.

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?

"Save a new automation" names a specific verb and resource, and the definition immediately narrows scope: the record is always created as a switched-off draft. It also distinguishes itself from update_automation by framing the call as creation, and names validate_automation and test_automation as separate steps.

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?

Explicit sequencing guidance is given: validate first, test afterwards, and the draft-off state means nothing executes until the user enables it. The quota note ("Counts toward the plan's automations") tells the agent there is a side effect on plan limits, which is exactly the kind of when-to-call context an agent needs.

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