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

Annotations already cover safety (readOnly, idempotent, non-destructive, closed-world), but the description adds real behavioral content: what each modality yields (fee, minutes-based ETA, minimum order, carrier, business-day ETA, free-shipping threshold) and how the unavailable case surfaces its reason. It stops short of stating error behavior for an invalid postal code or how the modalities are ordered/combined in the response.

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 purpose and the create_cart dependency before the modality breakdown, and every clause carries information. It is a single dense run-on sentence chain, though, which slightly hurts scanability for an agent parsing modality definitions.

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?

With no output schema, the description carries the burden of describing returns and does so reasonably: price, deadline, per-modality attributes, and the `note` field on unavailable. Missing only response shape/ordering and failure handling for a malformed postal code, which are minor for a read-only calculation.

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 100%, so the schema already explains storeId (from get_offers), postalCode, and items as {productId, quantity}. The description reinforces that shipping cost depends on item value and weight, and that pickup viability depends on store proximity, but adds no syntax or format detail beyond what the schema documents.

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 operation — computing how an order reaches the consumer's postal code with price and deadline for a given store — and enumerates the three distinct result modalities (pickup, delivery, shipping) it returns. It also positions itself relative to create_cart, so the agent can tell it apart from checkout/cart siblings without opening the 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 sequencing: call this before create_cart, present the returned options to the consumer, then pass the chosen option as `fulfillment` in create_cart. It also tells the agent how to interpret the negative case (available false → read `note` for the reason), which is the exact branch point an agent needs.

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