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

Goes well beyond the annotations: it discloses that authoritative=false rates are estimates rather than final charges, that cheapest_shipping_handle is null when rates cannot be compared in the cart currency, and that each top-level call opens a new card in the transcript. The credential requirement is also documented. Annotations (readOnlyHint=false, non-idempotent) do not cover any of this, and nothing contradicts them.

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, then the card preference, then the credential flow, so the important routing rule comes early. It is dense and a little long, with the credential repeated across the description and schema, but nearly every sentence carries operational information an agent needs.

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?

Output schema exists and return values are not restated, yet the one return-field semantic an agent actually needs (authoritative=false meaning estimates) is given. Combined with the address requirement, credential flow, and card-vs-chat decision, nothing needed to call this correctly 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 coverage is 100%, so baseline 3 applies, but the description adds real meaning: it states shipping_address must be supplied in the call and that the tool will not prompt for it, and it explains the agent_key credential's purpose and the alternative Authorization header path. That is value beyond the schema text.

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 ("Get available shipping rates for the cart") and immediately scopes it against the sibling flow by pointing to select_shipping_option territory via cheapest_shipping_handle. An agent can tell it apart from create_cart or select_shipping_option without opening a 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?

Explicit when-not-to-use guidance: prefer the cart card and let the buyer pick shipping there, only call directly when there is no interactive card or the buyer explicitly asks. It also names the checkout guide resource and the prerequisite create_sandbox_key tool, so the routing decision and the setup path are both unambiguous.

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