design_system_preview

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

Annotations already mark the tool as destructiveHint=true and readOnly=false, so the description's clarification that it does not save a library version/default or execute source code adds valuable behavioral context beyond the annotations. It also discloses the return contents: review draft, source warnings, and native specimen.

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 dense sentences deliver the core purpose, input encoding, output contents, and side-effect exclusions without wasted words. The action and scope are front-loaded, and every clause adds 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 no output schema and no parameter descriptions, the description covers the important behavioral points: accepted input formats, how files are supplied, what is returned, and what will not happen. The main gaps are the meaning of name and version and the precise shape of the 'review draft' and 'native specimen', but these are minor against the overall guidance.

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 schema description coverage at 0%, the description carries the burden for parameter meaning. It usefully explains that files are supplied as base64 and that a normalized system object can be provided, covering the files and system properties. However, it does not clarify the name or version parameters, leaving part of the parameter surface undocumented.

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 uses a specific verb ('Preview import') and enumerates the exact input resources: token JSON, CSS, static HTML, source ZIP, and portable Studio design systems. It also distinguishes itself from save/apply siblings by explicitly stating it does not save a library version/default.

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 makes the intended context clear: previewing an import rather than persisting it. The explicit statement 'Does not save a library version/default' signals when not to use it, but it does not name alternative tools such as design_system_save or design_system_apply, so it stops short of full routing guidance.

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