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

Beyond the annotations (destructive/idempotent/openWorld), it discloses the confirmation-token gate, token staleness behavior, the constraint that blank conditions cannot be re-enabled, and an approval-scope requirement. These are non-obvious operational constraints an agent could not infer from structured fields, and they are consistent with destructiveHint=true.

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 rule (apply the previewed change only) and every subsequent sentence adds a distinct constraint. It is dense and the 'Prepare a sparse change to an exact rule' clause is awkward and adds little, but there is no filler.

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 single-token, destructive commit tool, the description covers origin, validity, exclusions, and authorization scope, which is enough to invoke correctly. The absence of output schema is acceptable since results appear to be retrieved via the get_result sibling, though that retrieval path is not stated.

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 only one parameter and 0% schema coverage, the description carries the load: it says the tool 'accepts its confirmation_token only' and that the token must come from the preview after user confirmation, which explains origin and validity semantics. It does not cover token size/format limits, which the schema itself constrains.

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 ('apply the exact change... to an automation rule') and explicitly ties it to the preview_update_automation_rule sibling, so the agent knows it is the commit step of a preview/confirm pair. The phrase 'Prepare a sparse change to an exact rule' muddies the purpose slightly by describing preparation rather than application.

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 when-to-use ('after the user confirms that preview'), when-not ('changed or expired records require a new preview'), and an alternative path for a subclass of rules ('enabling/editing export/notification rules uses IPP'). 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.