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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint, so the 'Read-only' restatement adds little. The description does add real behavioral context beyond the annotations: the shared-hosting-only coverage boundary and the three fields returned (id, timestamp, size).

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 core action and its scope, then the ordering constraint, then the exclusion. The quoted user-phrasings earn their place by matching likely utterances; no filler sentences.

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, the description compensates by naming the returned fields and confirming read-only behavior. For a one-parameter list tool, everything an agent needs to select and call it correctly is present.

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 the single `domain` parameter is fully documented there with an example and account constraint. The description only reinforces the shared-site constraint implicitly, which is minor added meaning, so 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 resource ('Lists the restore points (daily backups)') plus scope ('one of the customer's SHARED hosting sites') and even the returned fields. It explicitly excludes VPS snapshots, so an agent can distinguish it from adjacent hosting tools without opening the schema.

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?

Gives explicit triggers ('what backups do I have?', 'can I roll my site back?') and a hard ordering rule ('ALWAYS before restore_my_site_backup so the backupId is a real one'), plus a when-not ('A VPS is not covered here'). Nothing is left to inference.

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