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

Annotations already flag a non-read-only, open-world, non-destructive call, so the burden is lighter; the description still adds real context: it is preview-only, it returns a plan_id, and Google must review the number before it serves. It does not say what confirming the plan does or whether a draft can be discarded, but the preview/review disclosures are genuinely additive.

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?

Front-loads purpose plus the PREVIEW warning, then the linking rules, then the review caveat — a sensible order with no redundancy. The trailing Google Ads API documentation link is boilerplate that does not help an agent decide or call, so it is not a perfect 5.

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?

With 8 parameters, an output schema and full annotation coverage, the description covers what an agent needs to call it correctly and sets expectations for the preview result. The only substantive omission is the downstream path — what to do with plan_id — which matters for a draft-style tool.

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 100%, so the baseline is 3, and the description earns a bump by explaining cross-parameter interaction the per-field docs treat only in isolation: the id chosen determines the linking target, and account scope requires both scope="account" and no id. The one gap is call_conversion_action_id's default behaviour, which appears only in the schema.

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 ("Draft a call asset") and immediately glosses the domain term as "a phone number shown with the ads." The closing "returns a PREVIEW" separates it from update_call_asset and from the apply step, so an agent can place it in the draft/confirm workflow 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 linking rules — ad_group_id links to that ad group, campaign_id to that campaign, and account-wide linking needs scope="account" with no id. It never names the sibling that consumes the resulting plan_id (confirm_and_apply) or states a when-not-to-use case, so it stops short of the top band.

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