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

Adds substantial behavior beyond the destructiveHint=true annotation: merge-by-clientRef semantics, deletion only via removeClientRefs, optimistic locking with draftId/expectedDraftVersion, server-side persistence and safe resume, and recoverable 429 responses that create no write plan. Nothing contradicts the annotations (omission never deletes, consistent with explicit removal), but the exact effect of a merge on previously supplied nested arrays could be stated more sharply.

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 dense paragraph of roughly 350 words mixing purpose, collection rules, continuation sequencing, error handling, and validation policy. Nearly every sentence carries information, but the lack of structure or grouping makes it hard to scan, and several points (AUTO negative support, family exclusivity) duplicate schema text.

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?

Covers the full lifecycle an agent needs: draft creation, incremental update with version locking, the multi-stage continuation ordering, AUTO bid mode decisions, recommendation handling, and the final confirm-and-apply path. With an output schema present, no return-value detail is owed.

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 already 100%, so the baseline is 3, and the description earns more by adding cross-field constraints the schema cannot express: one positive targeting family per MANUAL ad group, negative families gated by ad group type, and the requirement for a stable clientRef on every nested entity. Some of this restates the schema's own manualTargetingFamily and negativeTargetingMode descriptions, which caps it at 4.

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?

Opens with a specific verb and resource: 'Creates or incrementally updates an AD_STRUCTURE_CREATE draft', and immediately scopes it to SP Campaign/Ad Group/Product Ad structures. It is clear what the tool does, but it never names the narrower siblings (prepare_campaign_creation, prepare_ad_group_creation, prepare_targeting_creation) to explain when the umbrella draft tool is preferred over 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?

Explicitly states the transition points: call continue_workflow_draft when the draft is READY, pass applyContinuation to the operation-specific execution tool, and never ask permission merely to advance. It also gives when-not guidance (do not recreate an already-created structure when recommendations are rejected) and how to split both targeting families into separate structures.

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