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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=true, so the write-but-safe profile is covered. The description adds genuinely new behavioral facts: no provider/API call is made ('Kein Anbieteraufruf') and the operation is bounded by a previously confirmed ad limit, which tells the agent this only mutates prepared local state rather than live campaigns.

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?

A single front-loaded sentence with the verb first and the critical constraint ('Kein Anbieteraufruf') placed at the end for emphasis. The thirteen-item field list is long but each item maps to real schema fields, so little is wasted; only slight compression would improve it.

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 tool with a very large nested schema and no output schema, the description covers the configure branch well but leaves two notable gaps: the pause variant is undocumented and it does not say what a successful 'prepare' returns (presumably a prepared control key consumed by the apply sibling). It is adequate but not complete for a tool of this complexity.

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 0% and the 'request' parameter is a large oneOf, so the description does useful work by mapping many nested fields (budget, headlines, sitelinks, structured snippets, negative geo targets, locationMode, deviceModifiers, adSchedules) to human terms. But it omits the 'pause' branch of the oneOf entirely, omits guardrails/applyOfferPackage/applyQualityAction/conversionAction, and says nothing about offerKey or surfaceKey.

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 ('Bereitet ... vor') and enumerates the concrete resources being prepared (budget, ads, sitelinks, keywords, geo targets, device bids, schedules) and the scope ('für eine bestehende Kampagne'). The trailing 'Kein Anbieteraufruf' implicitly separates it from apply_search_ads_campaign_control without naming it, so differentiation is good but not explicit.

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?

'innerhalb der bestätigten Werbegrenze' hints that a confirmed ad limit must exist first, and 'Kein Anbieteraufruf' implies this is the pre-apply step. However, the description never names apply_search_ads_campaign_control as the follow-up, nor explains when to choose this vs. get_search_ads_campaign_control or when not to use it.

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