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

Goes well beyond the annotations: it discloses that the operation is additive ('existing ones stay'), enumerates what the preview returns (current windows plus account time zone), lists the validation rules that cause refusals, and warns that a campaign with no windows currently serves all hours, making its first windows an implicit restriction. The additive/safe profile is consistent with destructiveHint=false and readOnlyHint=false.

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 PREVIEW warning and the additive behavior are front-loaded, and the Google Ads API link is a reasonable tail. 'Returns a PREVIEW' and 'The preview lists...' is mild redundancy, but nearly every sentence carries operational detail.

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 an additive mutation with a preview step, the description covers what is preserved, what the preview contains, how removals are later addressed, refusal conditions, and the special empty-schedule case. With an output schema present, return-value enumeration is not required, so nothing essential is missing.

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 100%, so the schema already documents campaign_id, customer_id, and the full window shape including minutes and time zone. The description reinforces the time-zone semantics and adds the consequence of the first-window case, but repeats rather than extends the parameter documentation. Baseline 3 applies.

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?

Opens with a specific verb+resource ('Draft ad schedule windows for a campaign') and immediately qualifies the result as a PREVIEW, which separates it from apply-style siblings like confirm_and_apply. An agent can tell this drafts rather than commits without opening the 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 concrete routing: removal happens through remove_entity using the remove_id surfaced by the preview, and the first-window-on-an-unrestricted-campaign case needs a double confirmation. It also states rejection conditions (overlaps, more than six per day). It stops short of naming the confirm step tool explicitly, so the apply path is implied rather than stated.

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