Apply a ChatGPT Ads (OpenAI) plan

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

Annotations already declare destructive=true, readOnly=false, idempotent=false, but the description adds real behavioral detail beyond them: locks are re-checked, ops execute in order, execution halts at the first error, and every action is journaled. It stops short of stating irreversibility or recovery paths, which would be the remaining gap.

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?

A single tightly packed block, front-loaded with the operation type and precondition, then parameter sourcing, then execution behavior. Every clause carries information and nothing is redundant.

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 destructive write tool with no output schema, it covers preconditions, parameter provenance, execution ordering, fail-fast behavior and audit journaling. It does not address error recovery or the relationship to rollback_plan, leaving a minor completeness gap.

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 coverage is 100%, so the schema already documents all four parameters, giving a baseline of 3. The description reinforces that plan_id, confirmation_token and confirm must be passed unchanged from the plan_* tool, but adds no syntax or format detail and ignores client_id entirely.

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 precise verb and resource ('apply a signed plan'), names the platform (ChatGPT Ads/OpenAI), and prefixes the entry with 'WRITE:' so the operation type is unmistakable. It implicitly contrasts with the plan_* tools that produce the plan, letting an agent distinguish it from the other ~50 siblings.

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 a clear precondition ('after the user approved it') and tells the agent where the values come from ('exactly as the plan_* tool returned them'). It omits explicit exclusions and does not point to related siblings like rollback_plan or plan_get, so it stops short of full when/when-not routing.

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