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

Annotations already provide idempotentHint=true and destructiveHint=false. The description adds the no-publishing boundary and clarifies that the result is an AI-generated sample, which is useful. It does not, however, disclose what happens during preview, whether any non-published state is created, or what the output contains.

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?

One direct sentence front-loads the operation and the critical 'without publishing' caveat. There is no filler or redundant detail, and the structure is immediately scannable.

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 simple tool with one required enum parameter, the description covers the basic non-publishing contract. But with no output schema, no parameter guidance, and no routing to related email template tools, an agent still has meaningful gaps for fully correct invocation.

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?

The schema description coverage is 0% and the description never mentions email_type, request_id, or idempotency_key. The enum values help, but the text does not explain how email_type selects the template or what request_id and idempotency_key are for, so it fails to compensate for the schema coverage gap.

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 action ('Preview'), a specific object ('AI sample customization for a candidate email template'), and the key boundary ('without publishing'). It is clear enough to separate it from publishing or destructive template actions, though it does not explicitly distinguish it from the similarly named yardstick_email_templates_preview sibling.

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 conveys a preview context and the 'without publishing' constraint, so an agent can infer this is a pre-publish step. However, it does not name alternatives such as email_templates_publish, email_templates_validate, or email_templates_preview, nor does it give an explicit when-to-use versus other preview tools.

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