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

With destructiveHint already set, the description adds concrete behavioral detail: wholesale content replacement, unchanged settings/address, permanent redirect, slot-gated name minting, and grace-window behavior. This meaningfully goes beyond the annotation flags.

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 sentences, front-loaded with the core actioncars, then mode-specific behaviorholistic, then edge conditions. Every sentence earns its place with no repeated schema information.

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?

The description covers the two invocation modes, slot gating, grace-window support, post-condition redirect behavior, and irreversibility hints. For a mutation tool with no output schema and one required parameter, an agent has enough to call it correctly.

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?

Input schema already defines parameter names and coverage is high, but the description adds crucial relational semantics: exactly one of name/siteId must be chosen)Skip and what each mode does to the target site. This is value beyond the schema.

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 states a specific verb ('make permanent') and resource ('preview'), then clearly distinguishes two modes: minting a NEW site via name vs. replacing an EXISTING site via siteId. This clearly differentiates from sibling tools like discard_preview or publish_site.

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 description gives clear usage context: exactly one of name or siteId, behavior on live previews and expired previews still in the grace window, and the permanent redirect effect. It does not explicitly name sibling alternatives to route to, but the two-mode usage guidance is strong.

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