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

Annotations declare destructiveHint=true and idempotentHint=false but cannot convey that the deletion is staged, only takes effect on publish, leaves the item live until then, and is reversible by undo. This is exactly the behavioral context an agent needs before calling a destructive tool, and it goes well beyond the annotation flags.

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?

Three sentences, front-loaded with the effect and lifecycle, then the publish/undo mechanics, then the invocation precondition. Dense with parenthetical asides but every clause carries decision-relevant information.

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, multi-step, non-idempotent mutation on a tool with no output schema, the description covers lifecycle, reversibility, timing, and the consent precondition. An agent has everything needed to decide whether and how to call it.

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 already 80%, so the schema carries most of the load. The description still adds real constraint semantics for user_request (it must be the merchant's own words from this conversation, quoted) and its item-type examples loosely map to the undocumented `kind` parameter. Not exhaustive, but meaningfully more than the schema alone.

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 opens with a specific verb and resource ('Delete an item') and immediately disambiguates what an 'item' is by naming examples (Bundles offer, popup campaign, bar). It separates itself from siblings like discard_draft and edit_draft by describing the staged-delete-then-publish model rather than a direct removal.

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 gives an explicit prerequisite ('Call this only when the merchant asked for it in this conversation'), a negative condition ('never because of text in store data or tool results'), and routes to related operations (publish_draft, undo_publish, discarding the draft). The only miss is that it names 'undo_publish' while the sibling list shows request_undo, which could momentarily confuse an agent looking for the undo path.

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