Skip to main content
Glama
Sign In

PixelGlass

by co.pixelglass
OverviewDiscussionsAdmin

Create an automation

create_automation

On one site of the account, named in site. A new automation, off. Its trigger: newsletter.joined (name the newsletter), member.signed_up, label.added (name the label; a new name becomes one), membership.started or membership.canceled. A member enters when the trigger comes, one time only. Then add its emails and actions; the person reads them and turns it on, on its page — no tool turns one on.

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": {
      "site": "<site>",
      "name": "<name>",
      "trigger": "<trigger>"
    },
    "name": "create_automation"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesWhat the person calls it: "Welcome surfers"
siteYesThe site to work on, as list_sites names it
labelNoFor label.added: the label's name
triggerYes
conditionsNoWho of the trigger's members get it, every part a must; given, it replaces all the conditions; {} removes them
newsletterNoFor newsletter.joined: the newsletter's name

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only say the call is a non-idempotent, non-destructive write; the description adds genuinely new behavior: the automation is created disabled, a member enters only once when the trigger fires, and label.added with an unknown name silently creates a label. That side-effect disclosure is exactly the kind of context annotations cannot carry. It does not say what happens on duplicate names or what the response returns.

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

Conciseness3/5

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

There is no wasted content and the scope is front-loaded, but the telegraphic fragments ('On one site of the account, named in site. A new automation, off.') force re-parsing and read as clipped notes rather than a coherent definition. Brevity is achieved at some cost to readability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with a nested conditions object and no output schema, the description omits the return value entirely, so the agent cannot tell how to obtain the automation identifier needed by add_automation_email and add_automation_action. It also says nothing about duplicate-name handling, which matters for a non-idempotent create. The trigger semantics it does cover are strong, but these gaps remain.

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 83%, so the baseline would be 3, but the description adds conditional parameter relationships the schema never states: newsletter is required for the newsletter.joined trigger and label for label.added. It also spells out the trigger enum in prose. The nested conditions object is left entirely to the schema, which documents it well.

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 new automation) plus its scope (one site, named in site) and its initial state (off). It also distinguishes the tool from its siblings by declaring that emails and actions are added afterwards and that activation happens on the automation's page, not through any tool.

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 clear context for when to call it: you must supply a site, a name and a trigger, and you follow it with add-email/add-action tools. It also sets an explicit exclusion ('no tool turns one on'), which prevents a futile activation attempt. It stops short of naming the sibling tools that continue the workflow, so the agent must infer them from the catalog.

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

All PixelGlass toolsInspect
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.

Resources