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

Annotations already declare readOnly, non-destructive, idempotent, and closed-world, so the safety profile is covered. The description adds genuine context beyond that: what the render includes (merge fields that print nothing, personalization problems) and the explicit assurance that nothing is sent. It does not mention rate limits or whether previews affect any send metrics.

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 sentence, verb front-loaded, with the output contents listed after a colon and the no-side-effect guarantee in a short trailing clause. No filler and nothing an agent needs is buried.

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?

With no output schema, the description carries the burden of describing the return content and does so concretely, plus it rules out side effects. What's missing is minor: whether the preview consumes test-send quota or reflects the same render pipeline as an actual send.

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 coverage is 100%, so the baseline is 3, but the description adds real meaning the schema lacks: it clarifies that omitting contactId previews as 'you', and that a preview is rendered 'as one contact' would receive it. The variant enum and campaignId sourcing are left entirely to the schema.

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+resource ('Renders a saved newsletter') and enumerates exactly what the render contains (subject, preheader, plain-text, merge fields, personalization problems). The closing 'Nothing is sent' implicitly contrasts it with send_test_newsletter, but no sibling is named outright, so it stops short of full differentiation.

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?

Usage is only implied: an agent can infer this is the pre-send inspection step and that contactId previews as a specific person. There is no explicit 'use this instead of X when...' guidance against send_test_newsletter, check_newsletter, or get_newsletter.

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