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

Goes well past the annotations: every ad is created PAUSED, the preview_url expires after 24h, images are uploaded to OpenAI, each ad enters a review pipeline (in_review → approved/rejected), and an identical repeat call is idempotent. These are the failure modes an agent must know about for a mutation tool.

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?

Front-loaded with the two facts that matter most (beta, always paused, preview_url) before parameter notes. It is a single dense paragraph with no filler, though the run-on constraint listing could be broken up for faster scanning.

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?

An output schema exists, so return values need not be detailed, yet the description still flags preview_url and review_status. Combined with the review/idempotency behavior it is nearly sufficient for an 8-parameter mutation tool; only ad_group_id and any permission requirements go unaddressed.

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 must compensate, and it does for seven of eight parameters: internal-only name, title 3–50 chars, body max 100, https target_url, and the image_url vs. uploaded file_id alternative, plus the optional workspace slug rule. The required ad_group_id is never explained, leaving one material gap.

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 and resource — creating a ChatGPT chat-card ad on OpenAI Ads — plus the beta framing. This distinguishes it cleanly from the many sibling ad-creation tools (ads_create_ad for Google, meta_create_ad, linkedin_create_ad_from_post) without needing the 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?

Explicitly instructs showing the returned preview_url to the customer before activation, which is real usage guidance for this workflow. It does not, however, spell out when to choose this over the sibling ad-creation tools; the platform name only implies that routing.

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