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

Beyond the annotations it discloses the pricing/fee-quote sequence, the permission-dependent place-vs-draft behavior, spending limits, the required idempotencyKey retry protocol ('reuse the SAME value if you retry'), and the remaining venue-acceptance dependency. Notably it reconciles with idempotentHint=false by explaining that safety comes from the caller-supplied key, not from the tool itself.

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?

Dense and front-loaded: behavior first, then the draft path, then the idempotency rule, then tracking. It is longer than typical but nearly every clause carries operational weight; the 'Same rules and fields as draft_delivery_order' aside is the only mildly wasteful sentence, though it usefully avoids repetition.

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?

There is no output schema, yet the description names the key return values (draftId, orderCode) and the downstream calls that consume them, which is what an agent needs. Minor gaps remain around failure modes (payment decline, rejected venue) that would matter for a money-moving write.

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?

With schema coverage at only 44% across 9 params, the description compensates meaningfully: it explains the idempotencyKey contract, the allowed payment values, the selectedOptions shape for option groups, the connected-account requirement, and defers field details to draft_delivery_order. It does not, however, clarify the deliveryAddress vs savedLocationId tradeoff beyond what the schema already says.

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 states a specific verb and resource with scope: 'Orders food for delivery in one call.' It explicitly differentiates itself from draft_delivery_order ('same rules and fields') and confirm_delivery_order (which places the draft it returns), so an agent can route without opening sibling schemas.

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 gives explicit branching conditions: with full control it places immediately; if the person chose to confirm each decision it places nothing and returns a draft. It names the authoritative check (get_connection_permissions), the follow-up tool (confirm_delivery_order), and the tracking tool (check_booking_status).

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