Ads campaign create demand gen

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false and destructiveHint=false, so the safety profile is covered. The description adds real value with "one atomic call," signalling all-or-nothing semantics that no annotation conveys. However it silently omits the `confirm` parameter's gating behavior and the PAUSED default on `status`, both of which materially change what happens when the tool is invoked.

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 a colon-delimited inventory of what gets created; no filler, no repetition of the name. Every clause carries distinct information.

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 annotations cover mutation/open-world status. But for a 15-parameter, 10-required creation tool with zero schema descriptions, the definition leaves out the confirmation flow, default pause state, and any failure/partial-creation behavior an agent needs before calling it.

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 15 parameters, so the description must carry full explanatory weight and it only partially does: it groups parameters into budget, campaign, targeting, logo/image assets and multi-asset ad, which helps orientation. Critical semantics remain unexplained — the `confirm` gate, the `status` PAUSED default, micros units on daily_budget_micros/target_cpa_micros, whether geo_target_ids/language_ids are optional, and any minimum asset or headline counts.

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?

"Create a complete Demand Gen campaign" states a specific verb plus a specific campaign subtype, which cleanly separates it from ads.campaign.create_search and ads.campaign.create_pmax in the sibling list. The enumeration of what gets built (budget, campaign, ad group targeting, assets, multi-asset ad) makes the scope unambiguous, though the description never names those siblings explicitly.

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?

There is no guidance on when to choose this over create_search or create_pmax, no prerequisites (customer_id expectations, developer-token/auth requirements), and no statement about when a caller should use ads.mutate or ads.campaign.set_status afterwards. The word "atomic" hints at a preferred all-in-one pattern but never states it as a usage rule.

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