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

Annotations declare readOnlyHint=false and destructiveHint=false, so the description is not contradicting them. But the description adds no behavioral context beyond those flags—it doesn't disclose side effects, what happens to the referenced task, or whether this is a non-mutating preparatory step. Since annotations are present, the bar is lower, but the description still fails to enrich understanding.

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 a single sentence, but it is under-specified rather than concise. It lacks front-loaded critical information and contains no structured detail. Every word is generic and could apply to many tools, so it fails to earn its place.

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?

The tool has an output schema (indicated but not shown), yet the description provides no hint of what the output contains. It also doesn't clarify the workflow—whether this is a step before a confirm/deny pair (as seen in siblings like ads_replace_creative_prepare) or a standalone operation. Given the complexity of the domain and the existence of many related tools, this is severely incomplete.

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 0%, so the description must compensate for the parameters. It does not explain what task_ref refers to (a task ID from a create operation?) or what failed_items_only controls (whether to only recreate failed items). The description mentions 'prior create task' but gives no semantic link to the parameters, leaving the agent to guess.

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?

The description states a specific action ('prepare recreate') and resource ('from a prior create task'), which is not a tautology. However, it is vague about what 'prepare' actually accomplishes—whether it generates a draft, validates the task, or queues a recreation. It doesn't clearly differentiate from sibling tools like tasks_get_create_detail or campaigns_quick_create.

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 provides no guidance on when to use this tool versus alternatives. There is no mention of context, prerequisites, or exclusions. The single sentence gives no indication of when this is the right tool among the many similar prepare/confirm/deny patterns.

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