Create Lunch Order Draft

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

Annotations already establish readOnly=false, idempotent=true, destructive=false, so the bar is lower. The description adds genuine context beyond those: 'nothing is charged until pay_lunch_order_draft commits it' discloses deferred financial impact, and 'plus nothing else' rules out hidden fees. No contradiction with the annotations exists — the description never claims read-only or destructive behavior.

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?

Purpose is front-loaded and each sentence earns its place: purpose, usage criterion, pricing/behavioral detail, lifecycle alternatives, and a FINANCIAL confirmation warning. Minor redundancy exists between sentence one ('nothing is charged until pay commits it') and sentence three ('plus nothing else until pay_lunch_order_draft'), which could be merged without loss.

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?

Given the output schema exists (covering return values), the schema documents parameter provenance via get_lunch_menu and get_my_context defaults, and the description covers financial impact, lifecycle routing, and a confirmation warning, this is nearly complete for a financial write tool. The one small gap is that the description doesn't state what happens on repeat calls with identical arguments — though idempotentHint=true partially covers this.

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 schema documents all four parameters, justifying a baseline of 3. The description adds meaning on top: it explains the items structure as pairing a menu_item_id with a quantity and spells out the pricing computation ('sum of item prices times quantities plus nothing else'), which clarifies that price_cents is the unit price multiplied by quantity.

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 verb and resource — 'Creates an unpaid draft lunch order with one or more items' — and immediately distinguishes it from its lifecycle siblings: pay_lunch_order_draft commits it, update/discard change or abandon it. An agent can tell this tool apart from pay, update, and discard without opening any schema.

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?

Gives explicit when-to-use criteria ('Use for multi-item orders or when the user should review the total first') and names the alternative tools for the next action (pay_lunch_order_draft) and for alterations (update_lunch_order_draft, discard_lunch_order_draft). It lacks an explicit when-not-to-use statement for the direct single-item/pay-now case, but the guidance is otherwise clear.

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