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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds genuine behavioral context beyond them: pre-send verification of operation kind, approval integrity and state drift, plus the no-replay rule for uncertain outcomes. It does not say what permissions are needed or what a failure returns, so it stops 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, front-loaded with the action and scope, then preconditions, then the failure rule. No filler, though 'Confirm replace' is slightly awkward phrasing that costs a little clarity.

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 step with no output schema, the description covers preconditions, integrity checks and the reconciliation obligation — the essentials an agent needs. Missing permission/auth requirements and any indication of what a successful or failed call yields.

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). The description compensates partially by giving draft_id its provenance (must be a matching draft from prepare) and tying both ids to the operation, but connection_context remains undocumented in both schema and description. Baseline 3 for partial compensation under low coverage.

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: 'Confirm replace a campaign's start and end dates in its account timezone', with the two required identifiers named. It is clearly distinguished from its sibling google_ads_campaign_dates_update_prepare by being the confirmation half of the pair.

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?

Explicitly gates usage: 'Accepts only a matching draft from google_ads_campaign_dates_update_prepare', so the agent knows prepare must run first and the draft must match. It also states the rule for uncertain outcomes, but does not name the reconcile tool (google_ads_mutation_reconcile) that would satisfy 'reconciled without replay'.

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