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

Annotations already declare destructiveHint=true, openWorldHint=true and non-idempotent, so the safety profile is covered. The description adds real behavioral value beyond that: only unpaid drafts are deletable, and the operation waits for owner approval, meaning the call may not complete synchronously.

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 sentences, zero filler, with the destructive eligibility constraint front-loaded ahead of the approval caveat.

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 one-parameter destructive tool with full annotation coverage, the description supplies the two things annotations can't: eligibility scope and the approval wait. Remaining gaps (what happens to shipments within a deleted batch, error behavior) are minor.

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% and the single required parameter batch_id is undocumented in both schema and description. Its purpose is largely self-evident from the name, but the description's mention of 'or single shipment' creates ambiguity about whether batch_id can also reference a shipment, which is not resolved anywhere.

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 (Deletes) and resource (unpaid draft batch or single shipment), which lets an agent distinguish it from refund_batch and cancel_pickup by eligibility. It stops short of naming a sibling alternative for deleting paid/processed batches.

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 eligibility constraint ('unpaid draft') implies when the tool applies, and 'waits for the owner's approval' hints at an asynchronous flow. It never states what to use instead when the batch is not an unpaid draft, leaving the agent to infer the refund_batch path.

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