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

Annotations already declare readOnlyHint=false and destructiveHint=false, but the description adds real context beyond them: a private draft is saved after a Google validate-only pass and a complete affected-resource snapshot, and no change is transmitted. This explains why a 'remove/replace' operation is flagged non-destructive, which the annotations alone do not. It stops short of noting idempotency or draft expiry/lifetime behavior.

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 sentences, zero filler, and the identity of the tool (prepare, not send) plus the validate-only/snapshot behavior are front-loaded. Every sentence carries actionable information.

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?

For a prepare-step mutation tool with no output schema and a complex nested input, the description supplies the workflow context (draft, approval gate, confirm sibling) an agent needs to sequence calls correctly. The remaining gap is that the nested body structure is left entirely to the schema, which is acceptable given the schema's richness but not fully closed off.

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 33% and the description mentions no parameters at all – not customer_id, the body/asset_group_id/listing_tree shape, or connection_context. The 'listing tree' phrase loosely maps to the largest param but gives no syntax or format guidance, so the description does not 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?

The description states a specific verb+resource (prepare to remove and replace a Performance Max retail listing tree) and explicitly frames this as the non-mutating prepare half of a pair by naming google_ads_retail_tree_replace_confirm. An agent can distinguish it from the confirm sibling and from other google_ads_*_prepare tools without opening any schema.

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?

It gives explicit sequencing: call this to save a draft, then show the draft for explicit approval, then call google_ads_retail_tree_replace_confirm. It also states when-not in effect by clarifying that this call does not send the change, so the agent knows this is not the terminal action.

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