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

Annotations only supply the coarse safety profile (readOnly=false, destructive=false, openWorld=false); the description adds materially more — a Google validate-only pass, a complete affected-resource snapshot, a private draft, and the fact that nothing is transmitted. It does not cover prerequisites such as required connection permissions or draft expiry/staleness, which keeps 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, front-loaded with the action, followed by the side-effect disclosure and then the hand-off instruction. No filler or redundancy.

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/confirm mutation pair with no output schema, the description covers intent, side effects, and the transition to confirm — enough for an agent to call it correctly. It omits where the draft lives and how it is retrieved for review, which is a minor gap given sibling tools such as approval_plan_get exist.

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% (just customer_id), and the nested body object — campaign_id plus the intervals array with day/start_minute/end_minute, 15-minute multiples and a 42-item cap — is entirely schema-only. The description gestures at 'intervals' and 'campaign ad schedule' but adds no format, cardinality, or constraint detail to 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?

States a specific verb+resource ('prepare to remove the existing campaign ad schedule and replace it with the approved intervals') and explicitly contrasts itself with the sibling confirm tool. An agent can distinguish this draft-stage tool from google_ads_schedule_replace_confirm without opening either 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?

Gives explicit workflow guidance: run this to stage the change, then 'Show the draft for explicit approval before calling google_ads_schedule_replace_confirm.' It also states the negative case ('does not send the change'), so the when/when-not boundary is unambiguous.

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