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

Adds non-obvious behavior beyond annotations: resuming is free but each released page bills AI credits; the token's derivation from the hold proves evidence was read; and the drip stopped itself after poor search appearances. This aligns with readOnlyHint=false/idempotentHint=false and adds cost and accountability context annotations cannot express.

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?

The description is compact and front-loaded: the first sentence states the trigger condition, then the token requirement, the caution about fixing content, and the cost consequence. Each sentence carries new, decision-relevant information without filler.

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 conditional resume operation with an output schema, annotations, and a rich input schema, this description covers the complete decision context: when the hold occurs, what proves informed consent, what happens after resuming, and at what cost. No critical missing guidance remains for choosing or invoking the tool.

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 already covers all three parameters with 100% coverage, so the high-coverage baseline applies. The description adds extra semantic value for resumeToken—that it is derived from the hold and proves informed consent—beyond the schema's provenance note, though campaignId and user_intent get no additional description-level detail.

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 operation—resuming a page campaign only when the scale governor paused publishing—and explains the hold condition. This clearly distinguishes it from the many content/visibility/campaign siblings by defining the exact state and mechanism involved.

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 explicit when-to-use context: only for scale-governor holds, and requires passing the hold's resumeToken after reading evidence. It also warns to strongly consider fixing template/content first, defining when resuming is inadvisable, and notes the credit-billing consequence.

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