Execute reviewed subscriber tasks

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

Annotations declare destructive/non-idempotent/write, and the description goes well beyond them: prevalidate-all-then-verify-hash before the first request, stop-on-first-failure, no rollback, no retries, no implicit continuation, and it enumerates the failure return shape (known results, failed index, unattempted indices). This is unusually rich behavioral disclosure.

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 dense sentences, no filler, with the failure-handling contract front-loaded after the batch scope. The telegraphic phrasing is efficient though slightly clipped.

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 batch tool with no output schema, the description usefully specifies the failure result shape and the no-rollback guarantee. Success-path return details are absent, but annotations and the failure contract cover most of what an agent needs.

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 baseline is 3. The description does add that task order is significant and that the hash binds identical requests/profile/schema/order, but the schema already states 'exact ordered' and documents each parameter, so incremental value is modest.

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 identifies a specific resource (an ordered batch of subscriber/segment/workflow/custom-field tasks) and, together with the title, makes clear this executes rather than previews. It does not name preview_subscriber_batch directly, so the sibling boundary is only implied by 'Confirmed' and the hash requirement.

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?

It conveys the prerequisite state (tasks must be confirmed and hash-verified) and a hard constraint (no retries), which implies the preview-then-submit workflow. However, it never explicitly says to use preview_subscriber_batch first, nor states when not to use this tool.

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