draft_campaign

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

The description discloses that the operation is non-destructive (returns a preview, does not create), which aligns with annotations (destructiveHint=false). It adds detail about what entities are created in the preview (CampaignBudget, Campaign PAUSED, AdGroup, etc.) and what is excluded (Ads). This goes beyond the minimal annotation info.

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 well-structured with clear sections and bullet points, but it is quite lengthy. It front-loads the key information (draft, preview, no creation) and then provides detailed parameter explanations. While every sentence is informative, it could be slightly more condensed without losing clarity. Still highly effective.

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 complexity (15 parameters, 5 required) and the presence of an output schema (not detailed in description but exists), the description covers parameters, conditional logic, common values, and next steps. It does not detail the output structure beyond mentioning plan_id, but the output schema likely provides that. A bit more on return format would bump to 5.

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?

Despite 0% schema description coverage, the tool description provides comprehensive parameter semantics: lists bidding_strategy options, conditional requirements (target_cpa needed for TARGET_CPA, target_roas for TARGET_ROAS), explains keywords format, defines max_cpc context, and gives common geo/language IDs with examples. This adds significant value over the raw 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?

The description clearly states it 'Draft a full campaign structure — returns a PREVIEW, does NOT create anything.' It lists exactly what is created (CampaignBudget, Campaign, AdGroup, optional Keywords, targeting) and explicitly excludes Ads, distinguishing it from sibling tools like draft_responsive_search_ad.

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 explains when to use: to draft a campaign structure, and importantly, that it does not create anything. It provides explicit next steps: 'Call confirm_and_apply with the returned plan_id to execute.' It also notes that Ads are not included and recommends using draft_responsive_search_ad afterward, providing alternatives.

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