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

Annotations already flag destructiveHint=true, openWorldHint=true and idempotentHint=false, but the description adds real value beyond them: the spend implication, the meaning of a pending_review result ('awaiting review, not delivering'), and the reconciliation/retry policy. This is exactly the behavioral context an agent needs for a money-spending mutation.

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 most important signal (SPENDS MONEY) and densely packed with actionable guidance. It runs long with several clauses, but nearly every sentence carries distinct operational value, so the length is mostly earned.

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, open-world mutation with no output schema, the description covers the prerequisites (approval token, user confirmation), the result states (pending_review), and the retry/reconciliation policy. An agent has everything needed to call it correctly and safely.

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 0%, so the description carries the full burden and does so well: approvalToken is defined as the exact token from create/edit/get_chatgpt_ads, campaignId must be the same ID on retry to reconcile, and confirmed requires user approval. All three parameters gain meaning beyond the bare schema types and constraints.

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?

Opens with the critical fact 'SPENDS MONEY' and states a specific verb+resource: launching an approved ad draft or resuming a paused campaign. It clearly distinguishes itself from the sibling create/edit/pause/end_chatgpt_ad tools by naming them as token sources rather than alternatives.

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?

Specifies both supported flows (launch approved draft vs resume paused campaign), names where the approvalToken comes from (create/edit/get_chatgpt_ads), and states the confirmed=true prerequisite of user approval. It also gives explicit retry guidance ('repeat the same campaign ID... never create another draft as a retry').

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