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

Well beyond the annotations, it discloses that the restore creates a new commit rather than rewinding history, that the result goes live immediately, that a build theme rebuilds first unless the tree was already built, and that admin rights are required. One soft tension: annotations claim idempotentHint=true, while 'a new commit' per call implies repeated calls stack commits — worth clarifying but not a direct contradiction.

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?

There is almost no filler — each clause (commit semantics, live deploy, rebuild rule, admin gate) carries information. However the prose is written as sentence fragments stitched with em dashes and a parenthetical, so the key action is not cleanly front-loaded and sentences must be re-read.

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 three-parameter mutation with no output schema, it covers the important unknowns: history semantics, immediate liveness, build behavior, and permissions. It stops short of saying what is returned or whether a preview/confirmation step exists, which leaves a small gap.

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 only 33% (only `site` is documented), so the description must compensate. It does clarify that `sha` is a commit from theme_history and that `site` names one site of the account, but it says nothing about the `theme` parameter's expected form (name vs. id) or whether `sha` must be a full hash.

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 concrete verb and resource ('the rollback: the theme's files back to a commit from theme_history'), which is specific enough to distinguish it from siblings like update_theme or build_theme. The fragmented opening ('On one site of the account, named in site') delays the actual purpose slightly, but the operation is unambiguous once read.

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 implicitly routes the agent to theme_history as the source of the `sha`, and states an 'Admins only' prerequisite, which is genuine usage context. It does not explicitly say when to use this instead of update_theme, write_theme_file, or preview_theme, nor does it state conditions under which a restore should be avoided.

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