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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds the non-obvious facts: no implicit snapshot is taken, all progress since the backup is unrecoverable, an online server defers the change to next restart rather than applying it live, and a new backupId supersedes a queued restore. These are exactly the consequences an agent cannot infer from the hints.

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?

Three sentences, all front-loaded with the destructive consequence first, then the timing model, then the overwrite rule. Every clause carries information an agent needs; nothing is restated from the title 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?

With no output schema and only one argument, the description covers the destructive semantics, the deferral model, and the escape hatch, which is the bulk of what matters. The remaining gap is that the shape of the nested parameter object and the meaning of serverId are not addressed at all.

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 for the single top-level parameter (`path`) is 0%, and the description never explains that the argument is a nested object carrying backupId plus serverId, nor that serverId identifies the target server. It does add meaningful semantics for backupId (a different value replaces a queued restore) and points at createBackup/listBackups contextually, but the structural surprise is left to the schema.

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 states a specific verb and resource ("Replaces the whole world with the chosen backup") and immediately scopes what that means. It is clearly distinguishable from createBackup, cancelBackupRestore, and restartServer, which are named by role rather than left to inference.

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?

Explicit conditional routing: run createBackup first if you want to preserve the current world, cancelBackupRestore undoes a queued restore, and restartServer/restartToApplySettings is what makes an online server actually apply it. It also states the branch condition (asleep vs online server) that determines which path applies.

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