Delete a product across channels

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

Annotations already convey destructiveHint=true, readOnlyHint=false, so the description doesn't need to repeat those. It adds value by distinguishing 'Preview' (safe) from 'permanently delete' (destructive), giving a useful behavioral nuance. However, it does not disclose additional details like approval_token or confirm_delete requirements, which would have strengthened transparency.

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, tightly written sentence that conveys the core purpose without any filler or redundant details. It is concise and front-loaded, making it easy to parse quickly.

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?

Despite having an output schema and annotations, the tool's input command is complex with many nested fields (idempotency_key, approval_token, confirm_delete, expected_external_ids) and involves a safety-critical flow (preview vs execute). The description is far too minimal to guide an agent through correct usage, especially the distinction between preview mode and permanent deletion with confirmation requirements.

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 parameter meaning. It only hints at 'mapped product' (sku) and 'selected channels' (channels), but completely ignores required fields like idempotency_key and the confirm/dry_run/confirm_delete mechanism that are essential for proper invocation. This leaves the agent under-informed about the command structure.

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 clearly states the tool's function: 'Preview or permanently delete a mapped product across selected channels.' It specifies the action (delete), the resource (mapped product), and the scope (selected channels), making it distinct from sibling tools like product_stop or product_update.

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 implies usage for deletion or preview of deletion, but it does not explicitly contrast with alternatives such as product_stop or provide when-not-to-use guidance. It lacks clear exclusions or alternative tool references, so an agent gets only an implied context for use.

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