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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description goes well past that by naming the concrete consequences per mode: a deployment stop, a full file rollback, and a restart only if it was running, versus a non-disruptive copy into /restored-<date>/. It also discloses the asynchronous execution model and the polling target, which annotations cannot express.

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 operation, then mode semantics, then the async note — an efficient ordering with no filler. The telegraphic sentence fragments are compact but slightly compress the reading, and the async note comes last where it could arguably precede the mode detail.

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 destructive, asynchronous mutation with no output schema, the definition supplies the essentials: what gets torn down, that state is restored, and how to observe completion. Remaining gaps are the unlabeled `id`/`backupId` semantics and the absence of any note on reversibility or required permissions for a destructive operation.

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 only 25%, so the description must carry weight, and it does well for `mode` by explaining both enum values and their side effects. However, `id` and `backupId` — two of three required parameters — are never clarified (e.g. whether `id` is a deployment or volume identifier, and the relationship between the two), leaving the most error-prone inputs ambiguous.

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 resource ("Restore a restore point") and immediately decomposes it into the two concrete modes, so the agent knows exactly what operation it is invoking. It does not explicitly distinguish itself from siblings such as files_restore or backups_get, leaving that inference to the agent, which keeps it below a 5.

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?

"replace: stops the deployment... subfolder: copies the files... without stopping anything" gives the agent the operative trade-off (downtime vs. non-destructive copy) needed to choose a mode. It also states the async contract ("poll backups.list"), which is real usage guidance. There are no explicit when-not-to-use conditions or comparisons to the sibling restore tools.

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