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

Annotations already declare readOnly/idempotent/non-destructive, so the description's added value is the non-goals and the workspace authentication requirement — real context an agent needs before calling. The normalization behavior is named but not characterized (what gets corrected, whether input is echoed).

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?

Four short sentences, front-loaded with purpose followed by scope limits. Nothing is repeated from the title, though the fragment 'No persistence or mailing' is clipped to the point of being slightly under-specified.

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 an output schema, annotations, and a single nested parameter, the description covers the essentials: what it does, what it doesn't do, and the auth prerequisite. Only the relationship to the surrounding address/letter workflow (validate before send_letter, list_addresses for stored records) is absent.

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 0%, so the description must compensate; it only partly does. The 'U.S.' framing explains the country const 'US' and the formality of the constraints, but the required nested fields (name, line1, city, state, postal) and their patterns (2-letter state, ZIP or ZIP+4) are left entirely to the schema.

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 ('check and normalize') and resource ('U.S. postal address formatting'), and explicitly bounds the scope by ruling out deliverability/verification. It does not relate itself to any sibling (e.g. list_addresses or send_letter), so an agent must infer placement in the workflow.

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 is built from exclusions (not verification, no persistence, no mailing) rather than positive usage guidance; there is no 'use this before send_letter' or 'use list_addresses to read stored addresses instead.' The prohibitions do implicitly tell the agent when NOT to use it, which is more than nothing.

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