Draft AI Max settings

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

Annotations already mark this as a non-readonly, non-destructive, open-world operation, and the description adds substantial extra behavior: preview-only writes gated behind a plan_id, refusal of automations the caller never mentioned, requires_double_confirm for explicitly named automations, and the fact that campaign/ad group state is read before planning. This is far beyond what the annotations convey.

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 preview-scope statement is front-loaded and most sentences carry behavioral payload, but the quoted Google brand-list rejection message and the background about AI Max being the container for brand exclusions drift toward context that belongs with draft_prepare_brand_exclusions. Slightly long for the task, though not wasteful enough to obscure the core message.

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 complex 8-parameter draft tool this is well covered: the write-gating behavior, plan_id handoff, automation interactions, and paused-ad-group default are all explained, and an output schema exists so return values need not be described. Nothing critical for correct invocation is missing.

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, but the description adds real semantic value beyond the schema: it explains the interaction between the automation knobs (an unmentioned automation is refused, an explicit value like disable_search_term_matching=False or text_asset_automation="OPTED_IN" triggers requires_double_confirm) and frames include_paused_ad_groups behavior as protecting against silent search-term restoration.

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 first sentence states a specific verb (Draft), resource (AI Max controls), scope (Search campaign), and output modality (returns a PREVIEW), which cleanly separates it from siblings like get_ai_max_settings and confirm_and_apply. An agent can identify the tool's role in the draft/confirm pipeline without opening the schema.

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 makes the workflow explicit: nothing is written until confirm_and_apply runs, and the tool reads the campaign/ad groups itself so a prior getter call is unnecessary. It does not explicitly name get_ai_max_settings as the read-only alternative, so routing is strong but not fully spelled out.

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