AdCopilot

GTM: create trigger (staged, never published)

gtm_create_trigger

Create a trigger STAGED in the managed AdCopilot workspace (never published).

For a CUSTOM_EVENT trigger (type="customEvent"), give the dataLayer event it
fires on via `event_name` (convenience — builds the required customEventFilter
matching {{_event}} to that name) OR pass `custom_event_filter` as the raw GTM
condition list. `filter` / `auto_event_filter` carry extra firing conditions
for other trigger types; `parameter` passes trigger-type parameters through.

The first write to a container adds a draft workspace named AdCopilot
if it has none. AdCopilot has no Tag Manager publish permission, so
nothing reaches the website until a person publishes that workspace
in Tag Manager.

Tools revision: d80f65c0.

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": {
      "container": "<container>",
      "name": "<name>",
      "type": "<type>"
    },
    "name": "gtm_create_trigger"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes
`type`	Yes
`filter`	No
`container`	Yes
`parameter`	No
`event_name`	No
`auto_event_filter`	No
`custom_event_filter`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 23, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Adds meaningful behavior beyond the annotations: the write lands in a draft workspace, a workspace named AdCopilot is auto-created on first write to a container, and the integration lacks publish permission so nothing reaches the live site until a human publishes. This is exactly the consequential context annotations cannot convey. It does not address duplicate-name behavior (relevant since idempotentHint=false), which keeps it from a 5.

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?

Front-loaded with the key constraint (staged, never published) and organized into a parameter-choice paragraph and a workspace-consequence paragraph. Slightly redundant in restating "never published" in both the opening and closing sections, but no sentence is filler.

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?

An output schema exists, so return values need no explanation, and the staging/publish semantics of a write tool are well covered. The remaining gap is that an agent gets no hint about accepted `type` values or the container identifier format, which matters for a required parameter with no enum and no schema description.

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?

With 0% schema description coverage, the description carries the full burden and largely meets it: it explains `event_name` as a convenience that builds the customEventFilter matching {{_event}}, defines `custom_event_filter` as a raw GTM condition list, and scopes `filter`/`auto_event_filter`/`parameter`. The required `name`, `type`, and `container` params get no treatment, and no valid `type` values are listed.

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 trigger") plus the defining scope qualifier: it is staged in the managed AdCopilot workspace and never published. That qualifier alone differentiates it from gtm_update_trigger and gtm_list_triggers without the agent needing to open any schema.

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 concrete routing guidance among its own parameters: for type="customEvent" use either `event_name` (convenience) or `custom_event_filter` (raw condition list), and explains that `filter`/`auto_event_filter` apply to other trigger types. It does not say when to prefer this tool over gtm_update_trigger or what happens if a trigger with the same name already exists, so it falls short of explicit when-not guidance.

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

All AdCopilot 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.

Resources

Need Help?