Delete a delivery address

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

Annotations already declare destructiveHint=true, and the description reinforces this by explicitly stating 'Destructive: removes the address...'. It adds context beyond annotations by mentioning the need for user confirmation and the reliance on a one-time token, which is critical for a destructive operation. It does not contradict annotations, but could provide more detail on side effects, though the existing information is sufficient.

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 concise, with three sentences, each serving a purpose: the first explains the action, the second emphasizes destructiveness and user confirmation, and the third specifies token requirements. It is front-loaded with the core action and does not waste words, making it easy to parse.

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?

Given the tool's destructive nature and the existing rich annotations (destructiveHint=true) and full output schema, the description provides all necessary information for an agent to call it correctly: what it does, when to use it, prerequisites, and safety requirements. The output schema is likely to describe the result, so return values are covered. Nothing critical is missing for a safe and correct invocation.

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%, and the schema descriptions for parameters are clear (e.g., action must be an AppAction object, address_id is the id to delete, confirmation_token is a one-time token). The description reinforces the schema by explaining how action is obtained (from profile response) and how confirmation_token is used, adding practical context that helps the agent understand the flow beyond the schema's basic definitions.

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 that the tool deletes a delivery address from the Alza account, specifying the mechanism (per-address delete action from the profile response), the target (address_id), and the destructive nature. It distinguishes itself from siblings like address_upsert and address_search by being the delete operation, making its purpose unambiguous.

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 explicitly states when to use: only with explicit user confirmation, after showing which address will be deleted, and requires a one-time token from prepare_mutation. It also implies not to use without confirmation and refers to the action parameter as a prerequisite, effectively routing the agent to the correct flow.

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