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

Annotations already declare destructiveHint=true and readOnlyHint=false, and 'Cannot be undone' largely restates that. The one genuine addition is that this tool also restores a backup over the current templates — a destructive overwrite that a 'delete' tool name would not suggest. No permission, ordering, or approval context is added beyond what annotations and the confirm parameter already cover.

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 tightly-packed sentence with the resource scope front-loaded and the irreversibility warning last. Every clause carries information; the only minor cost is that bundling seven action modes into one sentence makes it dense.

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 10-parameter, seven-action destructive tool the description plus a very rich oneOf schema and destructive annotations gives an agent enough to call it correctly, and no output schema is needed here. What is thin is the operational context: ordering/prerequisites against templates_read and the backup-listing tools, and the fact that 'restore' is not a deletion.

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 description coverage is 100% and every parameter plus each action's required set is documented inline via oneOf, so the schema does the heavy lifting. The description adds no parameter-level meaning (no required-field callout, no id-sourcing hints) beyond what the schema provides. Baseline 3 applies.

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 enumerates the exact resource types it acts on (global blocks, menus, mail forms/fields, pages, backups), which is far more informative than the title alone. It also discloses the non-obvious restore behavior. It does not distinguish itself from the many sibling *_delete tools (content_delete, tmaker_delete, etc.), so the boundary of 'site design templates' vs other deletable entities is left implicit.

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?

No explicit when-to-use/when-not guidance and no naming of alternatives such as templates_write or the per-domain delete siblings. The enumeration of deletable entities only weakly implies the usage context, and nothing warns that restore_backup overwrites current templates rather than removing something.

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