Skip to main content
Glama

ADS Beast

prepare_google_conversion_action_create

Prepare creating a conversion action in a client's Google Ads account; the result carries the tag code for the site. Changes nothing: stores a preview_id (15 min, single use) to show, then execute_prepared_change.

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": {
      "client_id": "<client_id>",
      "name": "<name>",
      "reason": "<reason>"
    },
    "name": "prepare_google_conversion_action_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesConversion name, for example 'CRM signup'.
reasonYesWhy, with numbers (shown to the approver).
categoryNoConversion category.SIGNUP
client_idYes
account_idNoGoogle account id; needed only when the client has several.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false and openWorldHint=true, and the description explains why: nothing changes externally, but a preview_id is persisted — reconciling the write hint with the 'changes nothing' claim rather than contradicting it. It adds genuinely useful behavior beyond the annotations: the 15-minute TTL, single-use nature of the preview, and that the returned tag code is the site-side artifact.

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?

Two dense sentences, with the purpose and the no-side-effect guarantee front-loaded before the follow-up tool. The semicolon-clause structure is slightly compressed but nothing is wasted or repeated.

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 a 5-parameter prepare tool with no output schema, the description covers the mutation profile, the preview lifecycle, the return payload, and the execution path. The approval workflow (reason shown to the approver) lives only in the schema, a minor gap given this is an approve-then-execute pattern.

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 80%, so name, reason, category, and account_id meaning are already documented in the schema. The description adds only loose framing ('a client's Google Ads account') that maps to client_id and no extra detail on category choice or when account_id is required beyond what the schema states.

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+resource ('Prepare creating a conversion action') scoped to 'a client's Google Ads account', and immediately distinguishes itself from the sibling that follows it (execute_prepared_change). It also says what the result carries (the tag code for the site), so an agent knows both the action and the payload without opening the schema.

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?

Explicitly frames the two-step pattern: this tool changes nothing and stores a preview_id, then 'execute_prepared_change' performs the change. The preview's constraints (15 minutes, single use) tell the agent the ordering and timing requirements, leaving little to infer.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.