design_preview

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

With no annotations, the description carries the full burden of behavioral disclosure. It accurately describes the main actions (compose, review, run ERC, preview) and the 'preview' wording implies no commit occurs, but it does not explicitly state whether the tool mutates state or only reads pending changes.

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?

The description is a single, front-loaded sentence with no filler. Every action word contributes meaning and the overall structure is efficient.

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 there are no parameters and an output schema exists, the description covers the essential context: what the tool does, when to use it, and what it operates on. The only minor gap is the lack of explicit side-effect disclosure, but this is not critical for a preview-oriented tool.

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?

The tool has zero parameters, so there is nothing for the description to explain beyond the schema. The baseline for a parameterless tool is 4, and the description provides adequate context for how the tool operates even though it doesn't need to describe any arguments.

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 specific verbs ('Compose', 'visually review', 'run ERC', 'preview') and explicitly names the resource ('all pending changes') and timing ('before commit'). This clearly distinguishes it from siblings like design_commit and design_rollback, which handle committing or reverting changes.

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 phrase 'before commit' gives explicit usage context, telling the agent when this tool is appropriate. It does not explicitly name alternatives or exclusions, but the workflow position is clear enough to guide selection among the sibling tools.

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