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

Annotations cover the safety profile (destructiveHint=false, idempotentHint=true), and the description adds real behavioral context beyond them: ownership requirement, draft-status requirement, wholesale item replacement semantics, total recomputation from menu price times quantity, and an explicit WRITE/confirm-with-user instruction. The wholesale-replace wording is consistent with idempotentHint=true.

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?

Front-loads the action and scope, then hooks, then constraints, then the confirmation cue. Dense but every clause carries information; slightly overpacked with dash-separated conditions, though nothing is padding.

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?

An output schema exists so return values need not be described. Everything an agent needs to call this correctly is present: prior step, ownership, status gating, destination of replaced items, total recomputation, and the write-confirmation obligation.

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%, so the baseline is 3, but the description adds a genuine semantic constraint not spelled out in the schema fields: items must be passed as the COMPLETE list because they replace existing items wholesale, and the total is recomputed. order_id provenance (from create_lunch_order_draft) is also reinforced.

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+resource (replaces items/menu_date of an unpaid draft order) and scopes it precisely to pre-finalization drafts. It is clearly distinguishable from its siblings create_lunch_order_draft, pay_lunch_order_draft, discard_lunch_order_draft, and cancel_my_lunch_order.

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?

Explicitly states the preconditions (caller must own the draft, it must still be in draft status) and the when-not case with the alternative: 'once finalized, use cancel_my_lunch_order.' Provenance of order_id is named via create_lunch_order_draft, so the agent knows the whole flow.

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