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

There are no annotations, but the description still carries the full behavioral burden well. It explicitly states this is a non-mutating operation (nothing is created in the advertiser account) and that the budget is capped at the amount the user named. It also discloses the auth and rate-limit profile (50 per MCP session without login; 3 per day with no session number; 5 per day for named bots). These are exactly the constraints an agent needs before calling, and none of them appear in the schema.

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 is front-loaded in the first sentence with the deliverables enumerated, and the warning markers make the hard constraints easy to find. The final rate-limit sentence is dense, packing three tiers into one clause, but it is still short and every sentence earns its place.

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 3-parameter tool at 100% schema coverage, with no output schema, the description does cover the substance: it lists the draft's components and it states the non-mutation and the rate-limit constraints. What is left unstated are the shape of the returned draft, how long a run takes, and how the url is used (its content is fetched but not written), which are minor residual gaps.

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 description coverage is 100%, so the schema already documents url, media (with its default of all three), and daily_budget_krw. The description only reinforces the budget parameter with the note that exactly the amount the user stated should be used. That is a useful guardrail, but it adds little syntax or format detail beyond the schema baseline.

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 gives a concrete verb (creates drafts) plus the resource (an OpenAI·Google·Meta ad campaign draft) and enumerates the deliverables it contains: budget allocation, core messaging, keyword/context hints, and ad copy. It does not distinguish itself from the sibling analyze_site, which it also implies by describing the url parameter as 'a site to analyze'.

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 usage signals are implied rather than explicit: 'only makes drafts' and 'creates nothing in the advertiser account' tell the agent what it should NOT expect from the tool, and the rate-limit sentence explains the calling constraints. It never says when to pick this tool over analyze_site or check_ad_readiness, nor whether a site must be analyzed first, so the agent still has to infer the workflow order.

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