Plan an OpenAI Ads campaign (paused)

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

Annotations already declare readOnlyHint=true and destructiveHint=false, so the dry-run claim is consistent rather than novel. The description still adds real context: it never writes, a start_time is mandatory because otherwise delivery begins on activation, and financial guards (budget caps, currency locks, out-of-band human approval) apply. The financial clause is compressed to the point of ambiguity, which keeps this from a 5.

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 key fact ('PLAN (nothing is written)') and dense with useful content, but the line breaks fragment phrases mid-clause and the trailing sentence 'An OpenAI Ads key cannot be read-only' is cryptic and only loosely relevant.

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 planner tool with annotations covering the safety profile, a 100% documented schema and no output schema, the description supplies the workflow (plan -> apply -> activate in UI) and the constraints an agent needs. It does not say what the plan artifact returns, but plan_get/plan_list cover that.

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 baseline is 3, and the description adds scope meaning on top: status is always 'paused' (not a parameter), and no targeting/bidding/product-feed parameters exist. It does not clarify budget micros semantics beyond the schema, so it stays at a solid 4.

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 ('PLAN ... create one OpenAI Ads campaign') and immediately scopes it ('nothing is written', 'LOCAL dry-run only'). This separates it from openai_ads_apply and the other openai_ads_plan_* siblings without opening any 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?

Names the downstream alternative explicitly ('Apply with openai_ads_apply') and gives the condition for the next step ('activate it in the ChatGPT Ads interface once its ad groups and ads are ready'). It also states what is out of scope (no targeting, no bidding, no product feed).

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