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

The description adds meaningful behavioral detail beyond the annotations: items are replaced wholesale, the total is recomputed from price times quantity, and only unpaid draft orders can be updated. It correctly complements readOnlyHint=false and destructiveHint=false by framing the operation as a controlled, reversible-enough edit with ownership requirements.

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 information-dense and front-loaded with the core behavior, but it contains minor redundancy about draft status ('must still be in draft status' and 'Only draft orders can be updated'). Still, it earns its length by covering ownership, replacement semantics, and post-finalization routing in a compact form.

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 tool with 3 parameters, an output schema, and no nested objects, the description covers all essential context: what changes, what is required, what the preconditions are, how totals behave, and how to handle finalized orders. An agent has enough information to invoke the tool correctly and to avoid destructive mistakes.

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 100%, but the description adds crucial semantics beyond the schema: items must be the complete replacement list, the update replaces existing items entirely, and the total is recomputed from price times quantity. It also clarifies that order_id comes from create_lunch_order_draft, reinforcing the schema's provenance note.

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 states a specific action ('Replaces the items and/or menu_date') on a specific resource ('unpaid draft order'), and clearly scopes it to drafts not yet finalized. It also implicitly distinguishes this tool from siblings like discard_lunch_order_draft, pay_lunch_order_draft, and cancel_my_lunch_order by emphasizing draft-state editing.

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 explicitly says when to use the tool: the order must be owned by the caller and still in draft status. It also provides the alternative for finalized orders ('use cancel_my_lunch_order'), and instructs the caller to pass the complete items list and confirm with the user, giving clear operational guidance.

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