Ads campaign create search

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

Annotations already declare readOnlyHint=false, destructiveHint=false, openWorldHint=true, and idempotentHint=false, so the safety profile is covered. The description adds genuinely new behavioral context by calling the operation 'atomic', which tells the agent that partial failure will not leave orphaned budgets, ad groups, or ads behind. It omits the confirmation gate and default-paused state, which are the remaining behavioral gaps.

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 sentence with zero filler, front-loaded on the verb and resource, with the component list following as a compact colon-delimited enumeration. Every item earns its place by mapping to required inputs.

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 and annotations exist, so return values and the read/write profile need not be restated. But this is a 15-parameter, 7-required mutation that creates multiple entities at once, and the description says nothing about the `confirm` parameter, the default PAUSED status, non-idempotency (repeat calls create duplicate campaigns), or required account scope.

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?

With 0% schema description coverage, the description has to carry parameter meaning, and it does map most inputs to concepts: budget, bidding, geo/language targeting, negatives, keywords, and headlines/descriptions for the RSA. But it gives no formats or units (micros for daily_budget_micros/target_cpa_micros), no note that status defaults to PAUSED, no match_type behavior, and never mentions the safety-critical `confirm` parameter.

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 ('Create') and a specific resource ('a complete Search campaign'), then enumerates exactly what gets built: budget, bidding, geo/language targeting, negatives, ad group, keywords, responsive search ad. The qualifier 'Search' cleanly distinguishes it from siblings ads.campaign.create_pmax and ads.campaign.create_demand_gen.

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 phrase 'in one atomic call' implies this should be preferred over stitching together multiple mutate calls, which is useful routing context. However, it never states when NOT to use it (e.g., adding keywords to an existing campaign, or reusing an existing budget), nor any prerequisites for the customer account or the meaning of `confirm`.

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