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

Annotations only declare readOnly/idempotent/non-destructive; the description adds genuinely new behavior: draft retention of 24 hours, the state lifecycle, and what the error field means on failure. This is exactly the context annotations cannot carry.

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?

Four tight sentences covering state, follow-up actions, failure handling, and retention, each earning its place with no filler.

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?

No output schema exists, yet the description names the payload fields (ad_groups, primary_ad_group, error) and the 24-hour window, giving the agent everything needed to poll and act.

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% with draft_id already documented as the value returned by draft_ad_groups, so the schema carries the parameter. The description reinforces it by naming the originating sibling in prose, though it adds no new syntax or format detail.

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 (returns the state) and resource (a draft started by draft_ad_groups), with the exact possible states enumerated. Clearly distinguishes itself from the sibling draft_ad_groups (which starts the draft) and get_campaign_draft (a different draft resource).

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 names the sibling that starts the draft, and routes the agent on what to do in each state: pass ad_groups to add_ad_groups when done, start a new draft when failed. This is a model poll-then-act workflow description.

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