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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=false, so the description carries real weight and delivers: it discloses that this tool charges nothing (the guest pays on WaitApp's payment page), that a payment link is returned for online payment, that the venue must still accept the order, and that idempotencyKey is required and de-duplicates retries. The idempotentHint=false annotation is not contradicted — caller-supplied-key idempotency is a separate guarantee from blanket tool idempotency — and the description makes that distinction clear.

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-loaded with the core action and the permission branch, and every subsequent sentence (draft path, idempotency, payment link, venue acceptance) carries information an agent needs. It is dense and slightly overlong, with a couple of tightly packed clauses, but no sentence is filler.

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 complex, multi-branch mutation with no output schema, the description covers the important return shapes (draft summary with draftId, payment link, orderCode for tracking) and the post-placement lifecycle. It stops short of error/failure behavior and does not explain address-sourcing inputs, but nothing critical for correct invocation is missing.

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 description coverage is only 38%, so the description should compensate more than it does: it explains idempotencyKey's required/reuse semantics (already in the schema) and touches the payment field ('when payment is online'), but says nothing about deliveryAddress vs savedLocationId, guestName/guestPhone, items quantity bounds, or the other payment enum values. Baseline 3 is appropriate — it adds some meaning over the schema but leaves documented gaps.

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 first sentence names a specific verb+resource (order food for delivery) and immediately distinguishes this tool from its close siblings: quote_delivery (prices/quotes only) and draft_delivery_order (draft only), by stating it prices, quotes the fee, and then places. An agent can tell it apart 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?

It explicitly states the branch condition that selects behavior — permission chosen at connect time, visible via get_connection_permissions — and names the follow-up tool (confirm_delivery_order) for the confirm-each-decision path and track_order for post-placement. It also notes 'Same inputs and rules as draft_delivery_order', which routes the agent correctly between the draft and place variants.

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