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

Annotations already declare destructive, non-read-only, non-idempotent behavior. The description adds useful operational context beyond them: the machine must be stopped, the restore is asynchronous and should be polled via backup.restoring, and backup.restore_error must be checked first.

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?

Two dense sentences with no wasted wording, front-loading the key prerequisites. The polling and error-check instructions are compact and actionable.

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 restore with nested required parameters and no output schema, the definition covers preconditions and polling but omits the explicit restore action, parameter mapping, and overwrite or return behavior. The annotations cover destructiveness, but the overall definition leaves meaningful gaps.

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?

With 0% schema description coverage, the description must carry parameter meaning. It implies that the computer id and account backup copy are constrained, but it does not explicitly map to id/body.copy, explain formats, or describe the nested body.

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 never explicitly states that it restores a backup; it lists preconditions and polling behavior instead. The name 'backup_restore' and references to a backup copy and backup.restoring imply the action, but an agent must infer the core verb and resource.

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 concrete prerequisites (stopped computer, account backup copy) and says to inspect backup.restore_error before starting, which tells the agent when the tool is safe to invoke. It does not name alternatives or exclusions, but the precondition context is clear.

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