goods_receipt_reject_lines

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

With no annotations provided, the description carries the full burden of behavioral disclosure, and it does so thoroughly. It states that rejection causes no stock movement and no order quantity change, that the ordered quantity remains open and can be received later, that the reason is recorded with the actor on an append-only event, and that a non-pending line triggers an invalid_transition. These are precisely the side effects and failure conditions an agent needs to know, and they are all present.

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 three sentences, each carrying essential information. It opens with the core purpose, then explains the consequences, and finally states the constraint on line state. There is no redundancy or fluff. The structure is logical and front-loaded, making it easy for an agent to quickly grasp the key facts.

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 mutating tool with no annotations and no output schema, the description covers the essential context: when to use it, what effects it has on stock and order quantity, the requirement for a reason, the append-only event, and the invalid_transition condition. It does not describe the return value or how to obtain grId/lineIds, but these are likely external concerns. Overall, the description is sufficiently complete for an agent to call the tool correctly, with minor gaps around parameter acquisition and response handling.

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?

The schema provides no parameter descriptions (0% coverage), so the description must compensate. It explains that 'reason' is required and recorded with the actor on an append-only event, and it implies that 'lineIds' refers to the lines being rejected and that they must be pending. However, it does not clarify the meaning of 'grId', 'workspaceId', or 'idempotencyKey'. While some are self-evident from context, the description does not fully cover all parameters, leaving some ambiguity for an agent unfamiliar with the domain.

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 purpose: refuse HELD lines after a quality check. It specifies the action (refuse/reject), the resource (lines on a goods receipt), and the condition (HELD). It also differentiates from related tools like goods_receipt_accept_lines by explicitly contrasting with acceptance behavior (no stock movement, quantity stays open). The verb 'refuse' and the domain context make the purpose unmistakable.

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 provides clear usage context: it is to be used 'after a quality check' on HELD lines, and it explains that a non-pending line results in an invalid_transition, which guides when the tool is applicable. However, it does not explicitly name alternative tools (e.g., goods_receipt_accept_lines) or state when to use those instead. The guidance is implied rather than explicit, but still adequate for an agent to choose correctly in most scenarios.

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