Refuse an update

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

Annotations already declare destructive=true, idempotent=true and openWorld=false, so the safety and repeat-call profile is partly covered. The description adds one genuinely new fact, that the reason text is shown to the buyer, but says nothing about consequences for the order state or what happens if the request is later retried beyond what the requestId schema explains.

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 with the usage trigger front-loaded and zero filler; every clause contributes either the condition or the disclosure behavior.

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?

Covers purpose, trigger and the buyer-visible reason effect for a three-parameter destructive write, and no output schema exists that would need explaining. The one real gap is the unexplained 'id' argument, which an agent must guess at.

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% and both 'reason' and 'requestId' are already documented in detail in the schema, with the description only echoing that the reason is disclosed to the buyer. The 'id' parameter has no description anywhere, so its meaning (which order/update request) must be inferred.

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 ('refuses the update') plus the resource and the triggering condition ('seller will not change a delivered order as the buyer asked'). The 'delivered order' qualifier implicitly separates it from draft-update siblings, but no sibling is named explicitly.

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 opening clause 'Use this when a seller will not change a delivered order' gives a clear activation condition, which is the important half of usage guidance. It never states when not to use it or points to growwer_refute_seller_order_draft_update / growwer_request_order_update as the alternatives for non-delivered cases.

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