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

Beyond the readOnly/destructive annotations, it discloses the key scope requirement (deploy:write), warns that message content is data not instructions, explains live_from/live_until temporal semantics, and notes that times become approximate after rollbacks. These are substantive behavioral details an agent would not otherwise know.

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?

The description is dense but front-loads the core scope and ordering, then layers useful caveats about fields and time semantics. The single long paragraph is slightly run-on, but every clause carries operational value and there is no filler.

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?

There is no output schema, so the description carries the return-value burden and does so thoroughly by enumerating the fields and explaining active/live_from/live_until/rollbackable semantics. It also covers the key downstream usage with rollback, making the definition complete for this tool.

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 site and limit are already fully documented in the input schema. The description does not add parameter-specific semantics beyond implying site scoping; its value is concentrated in describing returned fields rather than input parameters.

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 clearly states the resource and ordering: 'The site's published versions, newest first,' and enumerates the metadata returned. It is effectively a list operation even though the verb is implicit, and it distinguishes itself from siblings like diff_versions and preview_version by focusing on version metadata rather than comparison or previewing.

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 concrete usage scenario — resolving a person's 'yesterday' by converting to UTC and selecting the version live at that time — and explicitly tells the agent to pass live_deploy_id as rollback's expected_live_deploy. It does not explicitly exclude or route against diff_versions/preview_version, so it falls short of full when/when-not guidance.

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