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

Annotations already declare readOnlyHint=true, destructiveHint=false, and openWorldHint=false, so safety is covered. The description adds genuinely new behavior: that addresses are validated and that the result is a widget containing a create-draft action, which tells the agent what the output is and what the next step should be. It stops short of mentioning cost, expiry, or what happens on validation failure.

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?

A single tight sentence pair, front-loaded with the 'use this to' cue and no filler. It is well sized, though the dense enumeration of three actions in one sentence slightly compresses detail that could have been spent on parameters.

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 17-parameter tool with nested address objects and zero schema descriptions, the description leaves the agent without guidance on how to supply addresses or which options exist. The output schema means return values need not be explained, but the input side is materially under-covered.

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 description coverage is 0% across 17 parameters with nested objects and three enums (sender/recipient_address_type, mail_class). The description says nothing about address types, manual vs. ID vs. text address forms, letter body limits, render options, or the request_id idempotency key, so it fails to compensate for the coverage gap beyond a vague nod to 'letter' and 'addresses'.

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 names a specific verb and resource ('preview ... a mailed letter') and enumerates the three things it does: renders the letter, validates addresses, and returns a widget. It implies separation from the create-draft siblings via 'non-writing preview' and 'before creating checkout', but never names postalform.create_letter_order_draft explicitly, so sibling differentiation is only partial.

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?

'before creating checkout' gives a timing/ordering cue for when the tool fits, which is real but implicit guidance. There is no explicit when-not clause and no named alternative among the many create_* siblings, so the agent must infer the routing itself.

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