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

With no annotations, the description must carry the full behavioral burden, and it does disclose the important non-obvious trait that this dispatches a real, irreversible physical letter and that markdown/text is rendered server-side. However, it omits the meaning of the `test` flag (a dry-run escape hatch is critical here), cost implications, delivery time, and failure/auth behavior.

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 with the core action front-loaded and the format/choice details following. No filler and nothing repeated from the schema.

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 7-parameter tool with nested objects, no annotations, and no output schema, the description covers the main happy path but not the remainder. It never says what the call returns or how the resulting letter is referenced later by get_letter_status, which the presence of `jobRef` strongly implies is important.

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%, so the description has to compensate. It correctly explains the four document input shapes and the service enum, plus the `from` requirement, but leaves `note`, `test`, `jobRef`, and the nested address object semantics entirely undocumented.

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 (mail a real paper letter in the Czech Republic via Česká pošta), including the provider and the physical nature of the action. This cleanly separates it from the sibling get_letter_status, which retrieves state rather than sending.

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 concrete conditional guidance ('Registered requires a `from` sender address') and names both service options, but never explains when to pick ordinary vs registered (cost, tracking, delivery guarantees). Usage context is implied rather than prescribed.

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