Prepare to initiate an existing experiment in SETUP. Saves a private draft after Google validate-only and a complete affected-resource snapshot; does not send the change. Show the draft for explicit approval before calling google_ads_experiment_initiate_confirm.
| Name | Required | Description | Default |
|---|---|---|---|
| body | Yes | ||
| customer_id | Yes | 10-digit Google Ads customer id. | |
| connection_context | No |
Changes observed during successful MCP inspections.
Input schema / properties / connection_contextAdded value: +{
+ "pattern": "^mctx_v1_[0-9a-f]{64}$",
+ "type": "string"
+}Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations only declare the safety triple; the description adds real behavioral context the annotations lack: it runs Google validate-only, persists a private draft plus a complete affected-resource snapshot, and critically does NOT send the change. This correctly reframes a non-readOnly tool as a non-mutating prep step.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three tight sentences, front-loaded with purpose then side effects then the approval gate. Every sentence carries information the agent needs to sequence the call correctly.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, and the description adequately covers behavior and the approval flow for a prepare tool. The main shortfall is the undocumented body/connection_context parameters, though they follow the sibling prepare conventions.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is only 33% (only customer_id is documented) and the description adds no meaning for body.experiment_id or connection_context. With a nested object and undocumented parameters, the description fails to compensate for the coverage gap.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Prepare to initiate an existing experiment in SETUP'), including the state constraint (SETUP) that scopes which experiments qualify. It explicitly distinguishes itself from its confirm sibling by naming it.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives an explicit workflow and precondition: call this first, show the saved draft for explicit approval, then call google_ads_experiment_initiate_confirm. The when-to-use vs the confirm alternative is unambiguous.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.