create_search_campaign

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

With no annotations provided, the description carries the full burden and delivers: the operation is atomic, the campaign is created PAUSED, a managed label is attached for later removal, location targeting is presence-only, an empty language list means 'all languages', and critically 'Dry run unless confirm=true' discloses the safety default. Network scope ('Google Search only (no partners, no Display)') and bidding behavior are also disclosed.

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 description is long but earned: 0% schema coverage and 11 parameters require this density. It is front-loaded with a one-sentence summary of scope and atomicity, then organized topically (label/paused state, locations, languages, bidding, network, structures, follow-ups, dry-run). Every sentence adds value, and the ad_groups/negative_keywords format specifications are presented compactly as inline JSON shapes.

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?

Given the tool's complexity - 11 parameters, 6 required, zero schema descriptions, and no annotations - this description is essentially complete. All parameter semantics, side effects (label, paused state), safety control (dry run), and follow-up tool routing are covered. An output schema exists, so the description's decision not to explain return values is appropriate per the rubric.

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%, so the description must fully compensate - and it does. It documents locations with concrete constant IDs (2840 = US), languages with IDs and empty-list semantics, bidding strategy combinations for target_cpa and cpc_bid_ceiling including currency and cap behavior, the complete ad_groups object structure, campaign-level negative_keywords structure, and the headline/description pin format. Nearly every schema parameter gains meaning beyond its bare name and type.

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?

The first sentence states a specific verb and resource: 'Create a complete Search campaign in ONE atomic mutate' and enumerates exactly what is included (budget, campaign, location/language criteria, negatives, ad groups, keywords, one RSA). It clearly distinguishes itself from piecemeal siblings like add_ad_group, add_keywords, and create_responsive_search_ad by positioning itself as the all-in-one atomic creation tool.

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?

The description explicitly routes follow-up work: device bid adjustments go to set_device_bid_modifiers ('the device criteria only exist once the campaign does'), extensions are 'separate tools - call them with the returned campaign id', and activation goes to set_status ('It is created PAUSED; enable it with set_status'). It also ties the managed label to remove_entity, giving the agent clear when-to-use-this-vs-sibling guidance.

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