Plan an OpenAI Ads budget change

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

Annotations only cover safety hints (readOnly true, destructive false, idempotent false); the description goes well beyond them by disclosing the financial cap, currency handling, the +20%/24h rate lock, the out-of-band approval requirement, the lifetime-budget refusal, and the LOCAL dry-run plus rollback semantics. That is exactly the behavioral context an agent needs before invoking a financial planner.

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 key fact (PLAN, nothing written) and keeps the rest dense but purposeful; every clause (financial cap, approval, apply, rollback) carries information. Slightly telegraphic run-on style, but no wasted sentences.

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, so the description carries the return-shape burden; it implies a plan artifact consumed by openai_ads_apply/rollback but does not say what the plan returns or how plan_get/plan_list relate to it. For a dry-run financial planner the behavioral coverage is otherwise strong.

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. The description adds financial context (client cap, currency) that helps interpret daily_budget_micros, but it also refers to the field as 'daily_spend_limit_micros' while the schema names it 'daily_budget_micros', a minor naming mismatch rather than added precision.

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 (PLAN/set) and resource (daily budget of one OpenAI Ads campaign), and immediately frames it as a non-writing operation. The platform-qualified name and the explicit 'nothing is written' clause distinguish it cleanly from sibling planners like gads_plan_budget_change and meta_plan_budget_change.

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 context and exclusions: lifetime budgets are refused, apply happens via openai_ads_apply, rollback restores the previous daily budget, and approval is out of band. It stops short of explicitly naming which sibling planner to use for a different ad platform, but the platform is unambiguous from the name.

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