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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds behavior the annotations cannot: it runs against the real site iframe bridge, treats experience players as labelled placeholders, disables sessions and paid effects, and explicitly does not save or publish. Those are meaningful operational facts an agent needs before calling.

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 action and mechanism, then usage rules, then parameter passing, then caveats. Each sentence carries distinct information, and no sentence is redundant with the schema or annotations.

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, but the description enumerates what a review returns (screenshots, layout, visible-control, image, and runtime diagnostics), and it closes the loop on side effects ('does not save or publish'). For a read-only inspection tool with complex runtime behavior, this is complete enough to call 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?

Schema coverage is 0% across four parameters, so the description must carry the load. It does explain 'the exact saved versionId' and 'an optional existing page with query/hash', covering two params (and even hinting at page format), but workspaceId and worldId are left to name inference, and it says 'versionId' where the schema names 'expectedVersionId'. Partial compensation merits a baseline 3.

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-plus-resource ('Review a saved hosted site draft') and then enumerates the concrete artifacts produced: desktop and mobile screenshots plus layout, control, image, and runtime diagnostics. This mechanism detail is enough to separate it from siblings like validate_hosted_world_site or get_hosted_world_insights without opening any 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?

It gives explicit timing ('once near the end of a new build or substantial redesign'), an explicit exclusion ('skip for small copy or metadata edits'), and an explicit follow-up budget ('at most one follow-up review on the affected page'). This is close to an ideal when/when-not/alternative statement.

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