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

With no annotations, the description must carry the safety profile, and it does: 'Sends nothing' rules out delivery, and 'checked the same way as saving' signals the same validation may reject the input. It also implies nothing is persisted by calling the output 'unsaved wording'. It doesn't state required permissions or what happens when only one of subject/body is supplied.

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?

Two sentences, front-loaded with what the tool does, then the parameter-driven behavior and the no-side-effect guarantee. Every clause earns its place with no repetition of 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?

An output schema exists, so return-value detail is unnecessary, and the description covers mode selection and side-effect safety. It leaves the meaning of the kind enum and the shop scoping implicit, which is a modest gap for a four-parameter tool with zero schema documentation.

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 must compensate, and it does well for subject and body: these are optional inputs that switch between preview modes. However, kind (a three-value enum) and shop_id are left entirely to the schema, and the coupling requirement that subject and body be supplied together is only implied by 'subject and body' phrasing.

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 combination: it renders one kind of automatic customer email with sample data and the shop name. That is clearly distinct from messages_saveTemplate or messages_templates, though it never names a sibling explicitly. The purpose is unambiguous without opening the schema.

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 conditional: supply subject and body to preview draft wording, omit them to preview the wording currently in use. That is real when-to-use guidance for two distinct modes. It does not point to an alternative tool for cases such as listing all templates or actually saving, so it falls short of a 5.

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