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

Adds substantial behavior beyond the annotations: read-modify-write semantics so untouched fields are preserved, that a new image_url replaces the current file, that creative edits trigger a new OpenAI review and halt serving while a name-only change does not, and that confirm=false returns a dry run. The destructiveHint/idempotentHint=false annotations are corroborated rather than echoed.

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-loads the action, then stacks only high-value facts (partial update, image replacement, review side effect, dry run) in short clauses with no filler or repetition. Density is high without being padded.

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 described, and the description covers the risky side effects well. The remaining gap is that with 0% schema coverage the meaning of account and the required ad_id are never addressed, which an agent calling an 8-parameter tool may need.

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 0% across 8 parameters, so the description must compensate, and it does for the important ones: title/body/target_url/image_url as editable creative, confirm=false as dry run, and the unlisted-fields-are-unchanged contract. It leaves account and the required ad_id unexplained, keeping it below a 5.

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?

Names a specific verb+resource ("Changes the copy, destination or image of an existing ChatGPT Ads ad") and immediately bounds scope as edits to an existing ad, which cleanly separates it from sibling create_chatgpt_ads_ad and the ad-group/campaign updaters. An agent can identify the operation without opening 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?

Gives clear when-to-use context (edit creative fields, use name-only edits to avoid a review restart, confirm=false for a dry run) and an explicit exclusion (ad cannot be moved to another ad group). It never names a sibling alternative to route to, so it stops short of a 5.

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