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

Annotations cover the safety profile, and the description adds genuinely new traits: atomicity ('all or nothing') and cost ('no AI and no credits'). It stops short of saying whether replace is reversible or that save_version is the recovery path, which would matter for an overwriting operation.

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 and dense with no filler; the atomicity and cost facts come first. The trailing action list is a long comma-separated run-on that is harder to parse than a bulleted form would be, but every clause carries 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?

Given two parameters, a single enum, and no output schema, the description is close to adequate, and delegating field discovery to guide() is a sensible strategy. However several action names (save_version, version_from_comments, diagram) are left entirely unglossed, so an agent must call guide before it can use them 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 100% and the description correctly says 'Fields go in params', matching the free-form params object in the schema. The pointer to guide({topic:...}) is useful for discovering per-action fields, but no action's fields are actually described here.

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 verb 'Change content' plus the enumerated action list makes it clear this is a mutation tool, and 'all or nothing, with no AI and no credits' distinguishes it from generation siblings. But 'edit' itself is generic and the description never names what resource is being edited (screens/designs) beyond the parenthetical mentions of HTML and React files.

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 real selection guidance among its own actions — patch is called 'the usual way' and scoped to 'one visual group per call', which steers behavior. It also points to guide({topic}) for required fields. It never states when to use edit versus siblings like design, import, or generate_media.

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