Ads campaign create pmax

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

Annotations already declare readOnlyHint=false, destructiveHint=false, idempotentHint=false and openWorldHint=true; the description adds the meaningful behavioral claim that the operation is atomic, so the campaign either fully exists or does not. It does not explain the confirm gate on a non-idempotent write, that campaigns default to PAUSED status, or any validation/permission failure modes, which are the details an agent most needs before firing a 17-parameter mutation.

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 that enumerates the bundled resources without filler; the colon-list structure makes the scope scannable. It runs long for one sentence and could be split so the atomicity guarantee stands out, but no clause is wasted.

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?

An output schema exists, so return values need not be described, and the description correctly focuses on inputs and scope. For a 10-required-parameter, zero-schema-documentation mutation, however, it leaves out the confirm/paused-default safety story and unit conventions, which are the gaps most likely to cause a mis-call.

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% across 17 parameters, so the description must carry semantics, and it does map roughly half the surface: budget, bidding, targeting, headlines/long_headlines/descriptions as text assets, images/logo_base64 as base64 assets, business_name as a brand asset. It never explains micros units for daily_budget_micros, the target_roas/target_cpa_micros tradeoff, the meaning of the confirm field, or the accepted bidding values, so a substantial portion of parameters remain opaque.

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 (create a Performance Max campaign) and enumerates exactly what the single call produces: budget, bidding, targeting, text and image assets, asset group, brand assets. The 'Performance Max' qualifier plus the 'atomic call' framing separates it from sibling campaign creators like ads.campaign.create_search and ads.campaign.create_demand_gen without needing to name them.

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?

Usage is only implied by the tool name and the asset list; there is no explicit statement of when to pick this over create_search or create_demand_gen, and no mention of prerequisites such as which customer_id to supply or when the confirm parameter applies. The parenthetical pointing to vertex.imagen.generate for image sourcing is a useful hint about upstream tooling but is not a when-to-use rule.

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