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

Annotations already declare this is a non-destructive, non-idempotent write, so the safety profile is covered. The description adds genuinely useful behavior: the pause is reversible via start_chatgpt_ad and is bounded by a deadline and remaining budget.

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?

Two compact sentences, front-loaded with the action, no filler. The resume detail is placed second, which is the right order.

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?

Covers reversibility and constraints, which matters for an unannotated-output mutation tool, but omits the sole parameter's meaning and the pause-vs-end distinction in a sibling set containing end_chatgpt_ad.

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% for the single required campaignId, and the description says nothing about it. Worse, 'the current user's ChatGPT ad' implies implicit targeting, which conflicts with the schema's requirement to pass an explicit campaignId.

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 (Pause) and resource (ChatGPT ad) with clear scope (the current user's ad). It names start_chatgpt_ad as the resume path, but does not distinguish itself from the sibling end_chatgpt_ad, which also stops an ad and could be confused with pausing.

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?

The description gives conditions for resuming (before deadline, within remaining budget), which implies pause is a temporary, recoverable action. It never says when to pause rather than end the ad, nor what prerequisites exist, leaving the key routing decision to inference.

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