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

Annotations already declare destructiveHint=true and readOnlyHint=false, so the safety profile is known. The description adds real value beyond that: it requires explicit approval, discloses internal verification of operation kind, approval integrity and state drift, and states a no-replay reconciliation policy for uncertain outcomes. It does not say whether the replacement is reversible or what a partial failure returns, keeping it short of a 5.

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, each carrying distinct information: action/scope first, then the input precondition, then verification and reconciliation behavior. No filler and the most decision-relevant fact (approval required) is front-loaded.

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 destructive confirm tool with no output schema and only safety annotations, the description covers the approval gate, validation steps, and failure-handling policy an agent needs. It stops short of describing the success/failure response shape or partial-application semantics, which are minor gaps given no output schema exists.

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 low (33%): only customer_id is documented in the schema. The description meaningfully clarifies draft_id by requiring a matching draft from the prepare tool, but says nothing about connection_context and adds no format or constraint detail for customer_id. Partial compensation for a low-coverage schema lands at the baseline.

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 (replace) and resource (Display, Demand Gen or App ad headlines and descriptions) with an explicit scope (the explicitly listed ad groups). It also names the sibling it depends on (google_ads_ad_text_update_prepare), so an agent can distinguish it from the prepare step and the many other *_confirm tools without opening schemas.

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 a clear precondition ("After explicit approval") and a hard input constraint ("Accepts only a matching draft from google_ads_ad_text_update_prepare"). It also implies the correct path for ambiguous results ("reconciled without replay"), though it never names google_ads_mutation_reconcile as the alternative, leaving the agent to infer the tool.

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