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

Beyond the sparse annotations, it discloses important behavior and consequences: 'paused is default; inherit may resume spend' warns of potential spend, and 'Prepare ... then launch_confirm after approval' signals this is a staging action, not a live launch. No contradiction with readOnlyHint/destructiveHint.

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?

Five short sentences front-load the core purpose and constraints, then finish with workflow guidance. No filler or repetition.

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 preparation/clone tool, the description includes the essential constraints, default behavior, sibling alternative, and follow-up approval step. The output schema covers return details, so the remaining omissions (start_time, engagement_mode variants) are minor for selection and correct invocation.

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 compensates for the key parameters: ad_account_id, exactly one source id, copies range 1-10, and status_option effect. It partially covers engagement_mode via 'keeping each ad's creative' but does not describe start_time or the new_creatives option.

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 opens with a specific action and resource: 'Prepare a same-account 1:1 campaign/ad-set tree clone, keeping each ad's creative.' It clearly distinguishes the tool from copy_ad_quick_copy by framing this as a tree clone while the sibling is for expanding selected ads.

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 gives explicit invocation constraints ('Pass ad_account_id and exactly one source_campaign_id or source_adset_id; copies=1-10') and workflow routing ('Use copy_ad_quick_copy to expand selected ads. Review exclusions, then launch_confirm after approval'). It tells the agent when to use the sibling and what to do next.

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