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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so safety is covered. The description still adds value by enumerating the possible states and what each carries (stage/percent for running, SiteVault's message for failure), which the annotations do not convey.

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 short sentences, front-loaded with the outcome states and ending with the read-only guarantee. Nothing is padded or redundant beyond the brief safety restatement.

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?

There is no output schema, so the description must describe returns — and it does, covering all three terminal/in-progress states and their payloads. Combined with the annotations, an agent has everything needed to call and interpret this tool.

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 50%, with site_id entirely undocumented. The description compensates by tying restore_id to 'the restore_id shown on the applied restore', telling the agent where to source the value; site_id is left implicit but is reasonably self-evident as the site being restored.

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?

Names the specific resource (a restore of one site) and the exact information returned: running with stage and percent, or completed/failed with SiteVault's message. This clearly separates it from fleet__restore_from_snapshot (which starts a restore) and fleet__undo_status (a different operation).

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?

The phrase 'the restore_id shown on the applied restore' implies the tool is called after a restore has been applied, giving an implicit usage context. However, it never states when to poll versus when to re-apply, nor does it name any sibling as an alternative or exclusion.

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