Select an AlzaBox / pickup point

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

Annotations already declare readOnlyHint=false, idempotentHint=false, and destructiveHint=false, so the agent knows this is a mutating, non-idempotent operation. The description adds valuable context: it updates the delivery selection for the current checkout session, does not submit the order, and requires a loaded mobile API access token. It also warns that the `association` object must be copied verbatim and never hand-crafted, which is a critical behavioral constraint. Minor gap: it doesn't describe the response shape or error conditions, but the output schema exists and the description covers the most important behavioral traits.

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?

The description is dense but well-organized. It front-loads the core action and then provides usage context, side effects, and prerequisites in a logical order. Every sentence earns its place: the verbatim-copy warning, the side-effect clarification, and the auth prerequisite are all essential. It's slightly long but not bloated, and the structure makes it easy to scan.

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 single-parameter mutation tool with a rich description and output schema, this is complete. The description covers the prerequisite (auth token), the source of the parameter (delivery_options response), the side effect (updates delivery selection), and what it does NOT do (submit the order). The output schema exists, so return values don't need to be described. The auth flow fallback is a nice touch that makes the tool self-contained.

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 documents the `association` parameter. The description adds significant meaning beyond the schema: it specifies that the object must be copied verbatim from the `delivery_options` response and never hand-crafted. This is crucial semantic guidance that the schema alone does not provide. The description also explains the parameter's role in the checkout flow, which helps the agent understand why it's required.

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 clearly states the action ('Associate a chosen pickup point... with the current checkout'), the specific resource (AlzaBox/AlzaShop pickup point), and the mechanism (submitting the DeliveryPaymentAssociation payload). It also distinguishes itself from siblings like `place_order` and `web_place_order` by explicitly noting it does not submit the order.

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?

The description provides explicit when-to-use guidance: use after `delivery_options` has returned the association object and the user has picked a concrete pickup point. It also gives clear exclusions: it does not submit the order (that is `place_order` or `web_place_order`). It even provides a prerequisite check (`account_status`) and fallback auth flow (`auth_start`, `auth_exchange`), which is exemplary usage guidance.

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