Prepare an irreversible campaign, ad-group, ad-group-ad, or keyword removal. Runs Google validate-only and returns the current entity snapshot; no change is applied.
| Name | Required | Description | Default |
|---|---|---|---|
| ad_id | No | ||
| ad_group_id | No | ||
| campaign_id | No | ||
| customer_id | Yes | 10-digit Google Ads customer id. | |
| criterion_id | No | ||
| entity_level | Yes | ||
| 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?
Explicitly discloses the irreversible nature of the operation being prepared and states that no change is applied and Google validate-only is run, returning an entity snapshot. This goes beyond annotations, which only claim destructiveHint=false (accurate for the prepare step) and readOnlyHint=false.
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?
Two tightly front-loaded sentences with no wasted words. The irreversible warning and the no-change guarantee are both prominent.
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?
The description covers purpose, safety, and lack of mutation adequately. However, with seven parameters and no output schema, it omits how to select the correct ID for each entity_level and what the returned snapshot contains, leaving gaps for an agent to infer.
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 very low (14%); only customer_id has a description. The description does not compensate by explaining which parameters (ad_id, campaign_id, etc.) correspond to which entity_level, or the connection_context purpose. Baseline 3 applies for minimal semantic value.
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 ('Prepare'), resource (entity removal), and the exact entity levels supported (campaign, ad-group, ad-group-ad, keyword). Clearly distinguishes itself from google_ads_entity_remove_confirm by the 'Prepare' prefix and the 'no change is applied' clause.
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?
Implies usage as a precursor to confirm ('Prepare an irreversible removal') and clarifies it is validate-only. It does not explicitly say 'use before google_ads_entity_remove_confirm' or list exclusions, but the prepare/confirm sibling pattern is transparent.
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.