Request changes to a delivery

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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=true, so the safety profile is covered; the description adds the useful state precondition (order must be awaiting review) and the fact that the reason is transmitted to the seller. It says nothing about what the request changes on the order, whether it can be withdrawn, or what happens if the seller ignores it.

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?

A single front-loaded sentence that leads with the usage trigger and folds the effect into the same clause. Slightly dense phrasing ('delivery of an order that waits for their review') but no wasted words.

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?

With three required parameters, no output schema, and a destructive write, the description covers intent and precondition but leaves the outcome and failure modes unstated. An agent knows when to call it but not what state the order ends up in afterward.

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 67% and both 'reason' and 'requestId' are well documented in the schema itself, so the schema does most of the work. The description only restates that the reason goes to the seller, adding no format, length, or identity semantics beyond what is already structured.

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 gives a specific verb+resource ('wants the seller to change the delivery of an order') and a concrete state precondition ('an order that waits for their review'), which separates it from neighboring tools like growwer_request_order_draft_update or growwer_refute_seller_order_update. It does not, however, name those siblings, so differentiation still requires inference from the name.

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?

"Use this when the user wants the seller to change the delivery of an order that waits for their review" provides an explicit trigger condition, which is more than most definitions offer. There is no when-not guidance and no pointer to the alternative path (refute/approve) if the order is not in review.

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