Request changes to a draft

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, and the schema's requestId text fully explains the replay semantics. The description's only extra behavioral fact is that the reason is transmitted to the seller, which the schema's reason description ("What the seller is told") already covers. Nothing is said about what state the draft returns to or whether the request can be withdrawn.

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 sentence, front-loaded with the usage trigger, with no filler. The phrasing "the draft of a post order that waits for their review" is slightly awkward but compact and information-dense.

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, idempotent mutation the annotations and schema cover safety and parameters reasonably, and there is no output schema to explain. What is still missing is the outcome of the call (what the seller receives, what the draft's new state is) and any clarification of the undocumented `id`. Adequate but not complete.

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 67%: reason and requestId are thoroughly documented in the schema, while `id` carries no description at all. The description adds nothing about any parameter — it does not clarify what `id` identifies (order id vs draft id), which is exactly the gap the schema leaves. Baseline 3 is appropriate.

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 names a specific action (request the seller change something), a specific resource (the draft of an order), and a pre-condition state (draft awaiting the buyer's review). That is enough to distinguish it from approve_order_draft or deliver_seller_order_draft, though it never names the near-identical siblings growwer_request_order_update or growwer_refute_seller_order_draft_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?

"Use this when the user wants the seller to change the draft ... that waits for their review" gives a concrete triggering condition and implicitly excludes drafts not in review. It stops short of explicit exclusions or pointing to the alternative tools for non-draft orders or for refuting a seller's counter-proposal.

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