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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the trailing "Read-only." is pure repetition and earns nothing. The genuine addition is the session-level sign-in requirement, which is behavioral context not encoded in any annotation, plus a hint of the returned field set.

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?

Two tight sentences, front-loaded with the purpose and followed by the precondition. The closing "Read-only." is wasted words given the annotations, keeping it just short of ideal.

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?

A zero-parameter, annotated read with an output schema — nothing an agent needs to invoke it correctly is missing. The description adds the one thing structured fields don't cover (session sign-in), and the field list is a harmless bonus.

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?

The tool takes zero parameters, so baseline is 4; nothing needs explaining and the description correctly spends no space on parameter semantics.

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 and resource ("Return the signed-in customer's saved delivery addresses") and enumerates the returned fields. It distinguishes itself from siblings like get_payment_methods by resource domain, though it doesn't explicitly separate itself from get_profile, which could plausibly contain address data.

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 gives a precondition ("Requires the customer to be signed in for this session") which effectively implies when the tool is usable, but it names no alternatives and offers no when-not guidance (e.g. use auth_status to check sign-in, use get_profile for other account data).

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