Design Screens Skeleton

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

Annotations already declare non-read-only, idempotent, non-destructive, and closed-world. The description adds the meaningful write-mode fact (write=true saves; default only returns) and the guard that an existing file is not replaced without overwrite, which is useful operational context beyond the hints.

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 purpose, then Use when, then behavior, then Returns. Every line is short and scannable; the Returns line is partly redundant with the existing output schema but is not wasteful enough to hurt.

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?

For a single-output generation tool with a documented output schema and full parameter coverage, the description supplies purpose, trigger, write semantics, and the overwrite guard. It omits where the design brief is located and any prerequisite on app.spec.json, but those live in the schema and sibling flows.

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%, so write, app_dir, and overwrite are already documented in the schema, including the overwrite-refusal behavior. The description adds only the onboarding-flow condition and does not deepen parameter semantics; baseline 3 is appropriate.

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 and artifact: produce the structural skeleton for design/screens.json, conditioned on the design brief's onboarding flow. It implicitly separates itself from visual authoring by noting 'the look is authored in Claude Design', though it never names a sibling such as design_generate, so differentiation is inferred rather than explicit.

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?

'Use when: starting design' gives a clear trigger and implies sequencing (this happens before look/visual work). It offers no explicit when-not or named alternative tools, so it falls short of a full routing rule but still gives usable context.

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