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

Annotations already declare destructiveHint=true and idempotentHint=false, so the safety profile is covered. The description adds two non-obvious traits the annotations cannot convey: the default-address guard and that deletion is gated on owner approval, meaning the call does not complete synchronously.

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?

Three short sentences, front-loaded with the action, followed by the blocking constraint and the approval behavior. No filler and nothing an agent must scroll past to find the critical restriction.

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 one-param destructive tool with no output schema, the key facts are present: what it removes, what it refuses to remove, and that it awaits approval. Minor gaps remain around whether the call returns a pending status or completes later, and what happens to shipments already referencing the address.

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?

Only one parameter and schema coverage is 100%, with the schema itself explaining that address_id comes from list_ship_from_addresses. The description adds nothing beyond that, but the baseline for a fully-documented single param is 3.

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 (Removes) and resource (saved Ship From Address), which cleanly separates it from the other delete_* siblings by resource type. It does not explicitly name an alternative, but the resource specificity makes the purpose unmistakable.

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 one concrete exclusion (the default address cannot be removed), which is genuinely useful pre-call guidance. However, it never points to the relevant alternatives such as set_default_ship_from_address or update_ship_from_address, so an agent blocked by the default-address rule is left to infer the next step.

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