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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the write/destructive profile is known; the description adds substantial context beyond that: atomicity ('if any part is refused, nothing is created'), duplicate-name rejection, image-ID validity and purpose requirements, budget currency and Google's 2x daily / 30.4x monthly spend behavior, ad review, and that campaigns cannot be deleted while images persist as assets. It also documents the confirmation_token lifecycle, the token cost per call, and the data_availability/access_error semantics. These are genuine behavioral disclosures, not restatements of the annotations.

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 core purpose is front-loaded and almost every sentence carries real information, but the whole definition is one dense run-on paragraph mixing creation semantics, budget math, result-handling conventions, and the confirmation protocol. Grouping the confirmation flow and the data_availability/prompt-injection guidance into separate sentences or blocks would make it far easier to scan.

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 15-parameter, 11-required mutation with no output schema, the definition covers everything an agent needs: prerequisite uploads, atomicity and failure modes, the mandatory preview/confirm handshake with token invalidation rules, and the fact that no_rows/access_error do not mean zero. Nothing material is left to inference.

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 coverage is 100%, so the baseline is 3; the description still adds value the schema does not: daily_budget_amount uses the ad account's currency unit (won for KRW), and the marketing/square/portrait image ID lists together hold at most 20 IDs, a cross-parameter constraint absent from the per-field maxItems. It also reiterates the no-quotes/no-backslash naming rule, but most remaining parameter meaning is already in the 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?

States a precise verb and resource ('Create one Demand Gen campaign') and enumerates exactly what is created in the single request: budget, PAUSED campaign with Maximize conversions bidding, ad group, image ad, and image assets per uploaded image. This cleanly separates it from the sibling create tools for display, pmax, and search campaigns.

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?

Explicitly says images must be uploaded first with their upload IDs, that a fully-running campaign requires the Demand Gen campaign update tool to set ENABLED, and that a call must not be retried when the outcome is unknown because a second call creates a second campaign. It also spells out the two-step preview/confirm flow and the rule that the token may never be added without user agreement.

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