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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so the safety profile is covered. The description adds one genuinely non-obvious behavioral fact — enquiry submission is disabled in the returned HTML — but says nothing about access requirements for private drafts or how the preview relates to saved vs. unsaved edits.

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 compact sentence with the return value front-loaded and a qualifier appended. No filler, no repetition of the tool name or annotations.

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 zero-argument, read-only tool with rich annotations and no output schema, the description covers what is returned and one behavioral caveat. It omits what happens when no draft exists and how the result differs from get_site, which are the remaining questions an agent would have before calling it.

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 tool takes zero parameters, so there is nothing the description needs to disambiguate at the argument level. Baseline of 4 applies for a no-parameter tool.

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: 'Return private draft preview HTML', which is clearly distinct from mutating siblings like publish_site or save_site. It doesn't explicitly contrast with get_site, so the agent has to infer the draft-preview vs. live-site distinction.

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 word 'preview' and 'draft' imply the use case (inspecting unpublished content before publishing), but there is no explicit when-to-use statement, no mention of prerequisites, and no named alternative such as get_site for published content. Usage is inferable rather than stated.

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