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

Beyond the annotations (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true), it discloses the atomic all-or-nothing create for group/keywords/ads, best-effort follow-up for assets/audiences/devices with per-item failure reporting, the guarantee that the source is never changed, the confirm=false dry-run preview, and the 25-id cap. This is materially more than the structured fields provide and is consistent with them.

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 purpose and the alternative it replaces are front-loaded, and every sentence carries content. It is a dense single block, however, and the long enumeration of copied fields plus the parameter notes could be split for faster scanning; nothing is wasted, but structure works against it slightly.

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 13-parameter mutation tool, it covers atomicity, partial-failure semantics, defaults, preview mode, source immutability, and limits, and an output schema exists so return-value shape need not be described. An agent has everything needed to call it correctly and safely.

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 carries the full burden and does explain ad_group_ids (one or comma-separated, up to 25), target_campaign_id constraints, status values including KEEP, new_name vs name_suffix default behavior, and cpc_bid > 0 semantics. It leaves the include_ads/include_keywords/include_negatives/include_assets/include_audiences toggles and customer_id unexplained, so coverage is good but not complete.

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 description states a specific verb (copies), resource (Google Ads ad groups), scope (into another campaign of the same account, or duplicated within the same campaign), and enumerates exactly what gets copied. It also distinguishes itself from the manual rebuild path (create_ad_group + add_keywords + create_responsive_search_ad), so an agent can identify it without opening a 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?

It explicitly positions itself against the alternative workflow ('instead of rebuilding each group with...'), gives the hard constraints that select/deselect it ('target_campaign_id must be in the same account and of the same campaign type'), and notes that non-RSA ad types are skipped. That is clear when-to-use, when-not, and alternatives in one pass.

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