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

Annotations already cover readOnly/idempotent/non-destructive, and the description adds genuinely new behavioral context: it is free ('costs nothing and needs no key') and it describes the shape of the response (rules, counts, worked example). The concrete SHAMONG vs SHAMONG TOWNSHIP case also warns that some alternate names are not mailable.

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 tight sentences: the concept first, then the concrete distinction that carries the real information, then the return shape and cost. Nothing is redundant and the key caveat (invalid alternates) is front-and-center.

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?

With no parameters, no output schema, and a purely informational scope labeled by annotations, the description covers everything an agent needs: what it explains, what it returns, and that it is free and keyless.

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 there is nothing for the description to disambiguate; the baseline for a no-parameter tool applies. No parameter text is needed.

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 states a specific resource and what is returned: 'Returns the rules, the counts and a worked example' about how USPS assigns preferred and alternate city names per ZIP Code. It is clearly a reference/meta tool, distinguishing it in spirit from data tools like zip_lookup, though it never names a sibling explicitly.

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?

Usage is implied by 'which of those names may be used on mail' — an agent can infer this matters before address validation or when interpreting a city name. However, there is no explicit when-to-use/when-not-to-use statement and no named alternative such as validate_address or zip_facts.

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