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

With no annotations provided, the description carries the full behavioral burden. It discloses the crucial traits: the operation is irreversible, it only runs Google validate-only, it returns the current entity snapshot, and no change is applied. This gives an agent a solid safety picture, though it does not mention permissions or side effects beyond the snapshot.

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?

The description is a single, tight sentence that front-loads the core purpose and then adds the critical safety qualifiers. Every phrase adds information, and there is no filler or repetition of schema details.

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 tool has six parameters, only two required, no output schema, and no annotations, yet the description omits the parameter-selection contract needed to invoke it correctly. An agent still must infer which ID to provide for a given entity_level and how to combine fields, which is a significant completeness gap.

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 description coverage is only 17%, so the description must compensate, but it does not explain which ID field corresponds to which entity_level or whether exactly one ID should be supplied. The entity type names in the description ('ad-group', 'keyword') hint at parameters, but ad_id, ad_group_id, campaign_id, and criterion_id remain semantically ambiguous.

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?

The description states a specific action ('Prepare... removal'), a clear scope (campaign, ad-group, ad-group-ad, keyword), and distinguishes this from the actual destructive action by saying it runs validate-only and returns a snapshot with no change applied. The mapping to the schema's 'responsive_search_ad' enum is slightly loose, but the intent is unmistakable.

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?

The description implies this is a preflight step because it says 'no change is applied' and 'prepare,' and the sibling google_ads_entity_remove_confirm clearly handles the actual removal. However, it never explicitly says 'use confirm to apply the removal' or gives when-to-use/when-not-to-use guidance, leaving that largely to inference.

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