Set up labsUI

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

Beyond the annotations, the description discloses the concrete artifacts written, that existing files are preserved on re-run (a stronger statement than idempotentHint), the prerequisite stack (React 19, Tailwind v4), and the return payload (warnings, files written, root layout code to add). No mutation of user files is hidden from the agent.

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?

Roughly three sentences with no filler: what it writes, what it returns, prerequisites, and repeat/preview behavior in that order. The critical 'once, before add' constraint is front-loaded in the first clause.

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?

Even with no output schema, the description names what comes back (warnings, files written, root layout code). Combined with prerequisites and idempotency behavior, an agent has everything needed to decide whether and how to call it.

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 at 100% schema coverage the schema already defines dryRun fully. The description's 'dryRun previews' reinforces the intent in the context of this specific tool, but adds little beyond the schema's 'Report what would change, write nothing.'

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 the specific action (scaffold labsUI into a project) and enumerates exactly what it produces: styles, theme, utils, motion provider, a labsui.css import in the Tailwind stylesheet, and a labsui.json settings file. It also positions itself relative to siblings by saying it runs 'once, before add', so an agent can separate it from add, doctor, and update 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?

Gives explicit ordering ('once, before add'), a fallback path ('run doctor first if unsure'), and a preview option ('dryRun previews'). The 'safe to repeat' clause tells the agent it need not guard against re-invocation, which is exactly the decision point an agent faces with a setup tool.

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