Skip to main content
Glama

Tag Manager setup and tracking check

tag_manager_setup
Read-only

Inspect a Google Tag Manager container's tags, triggers, unpublished changes, and setup issues to diagnose missing or incorrect conversions without making changes.

Instructions

A container's tags (what each sends where, and when it fires), its triggers, what isn't published yet, and issues: tracking problems worth fixing, such as a Google Ads conversion tag with no Conversion Linker or firing on every page, a tag that never fires, or retired Universal Analytics. Use it when conversions are missing or look wrong. Changes nothing.

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": "tag_manager_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
containerYesThe container, as tag_manager_containers lists it, e.g. accounts/123/containers/456

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.32.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true, openWorldHint=true and destructiveHint=false, and 'Changes nothing' restates that safely. The real added value is explaining the `issues` payload with concrete failure modes (Google Ads conversion tag missing a Conversion Linker, tag firing on every page, tag that never fires, retired Universal Analytics), which tells the agent what signals come back. It does not describe result size, ordering, or how unpublished items are marked.

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?

The opening is front-loaded with the inventory of what comes back and the usage trigger lands early, which is good structure. However, the first sentence is a verbless fragment with a stray colon list, and the four-item `issues` example set is longer than needed to convey the concept.

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?

With one parameter, no output schema, and full annotation coverage, the description carries the burden of describing returns and it does so at a useful level of detail. It leaves minor gaps (whether unpublished items are separated from published ones, whether issues are severity-ordered) but nothing that would cause a mis-call.

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 coverage is 100% on the single `container` parameter, including the required `accounts/{id}/containers/{id}` pattern and an example. The description adds nothing about the parameter, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description enumerates concrete resources returned (tags, their destinations and firing, triggers, unpublished items, `issues`) and implicitly contrasts with a mutation path via 'Changes nothing'. It never states a verb ('returns'/'lists'), so the first sentence reads as a noun-phrase fragment rather than an action, which slightly blunts clarity. An agent can still tell this is the read-side setup/audit tool, distinct from propose_tag_manager_changes.

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?

'Use it when conversions are missing or look wrong' gives a clear situational trigger, and 'Changes nothing' signals that mutation belongs elsewhere. It stops short of naming an explicit alternative or exclusion, so the agent must infer that fixes go through a propose tool rather than being told so.

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