Apple Preview Communication

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

Annotations already declare readOnlyHint and idempotentHint, and the description's 'Preview ... before sending' is consistent with no side effects. It adds little behavioral context beyond the preview nature, but no contradiction and no need for destructive-operation warnings.

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 front-loaded sentence with no redundant phrasing. It captures action, resource, timing, and channel context efficiently.

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?

The output schema and read-only annotations cover return values and safety, and the description covers purpose and timing. However, given 6 parameters with 0% schema coverage, the lack of input semantics leaves the definition incomplete for correct invocation using optional parameters.

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% and the description provides no parameter-level guidance. Required fields like recipient and message are self-explanatory, but optional fields such as preferred_channel, from_account, and attachments lack semantics or allowed values, so an agent cannot reliably invoke with them.

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 uses a specific verb ('Preview') and resource ('communication') and states the scope ('route ... before sending it through Messages or Mail'). This makes it clearly distinct from actual send/prepare siblings.

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?

It gives a clear usage context: use this when you need to see routing before delivering via Messages or Mail. It does not explicitly name alternatives or state when not to use, but the 'before sending' phrasing effectively separates it from send actions.

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