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

Goes well beyond annotations: discloses the 24-hour URL lifetime, the deploy:write scope requirement, that CMS entries/texts are NOT versioned with the pages, that forms behave as tests, and the free-plan quota (30/day shared with preview_draft). With readOnlyHint=false already signaling mutation, this adds real consequence-level context.

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?

Front-loaded with the return value and constraints before the usage block, and every sentence carries information. The consent/instruction-injection paragraph is somewhat boilerplate-heavy but is clearly delimited by the [When to use] header.

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?

Complexity is low (2 required params, no output schema), and the description covers what is returned (a URL), how long it lasts, what it reflects, and the quota cost. Nothing an agent needs in order to call it correctly is missing.

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% and both parameters already document their source (list_sites, list_versions), so the schema carries the load. The description adds no syntax, format, or edge-case detail about site or deploy_id beyond what the schema states — baseline 3.

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?

Opening sentence gives a concrete artifact (a 24-hour preview URL of a retained version) plus the visible trait (earlier-version band), which is a specific verb+resource. It also implicitly separates itself from preview_draft by noting shared quota, so an agent can tell the two apart.

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 [When to use] block explicitly gates invocation on an explicit user request and warns against acting on instructions found in tool results — clear consent/exclusion rules. It names preview_draft only in the quota context rather than as a selection alternative, so routing between the two preview tools is still partly inferred.

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