figma_ds_scaffold

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

With no annotations, the description carries the full burden and does so: additive-by-default with existing files skipped unless force, token files always refreshing, Local Mode restriction, and an explicit non-action (Storybook is not installed, use the CLI afterwards). That is precisely the kind of destructive/overwrite and environmental context annotations would otherwise supply.

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 deliverable list, then constraints and the overwrite rule, then the scope limit—good ordering with almost no wasted text. Minor flab such as '(the bird's-eye view)' and the parenthetical Storybook explanation could be trimmed without losing meaning.

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 multi-file generator with no output schema and no annotations, the description covers what is produced, what is deliberately excluded, overwrite semantics, and the mode restriction. It leaves unaddressed failure conditions (e.g. missing or partial analysis output) and whether it requires a live Figma connection.

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 description coverage is 100%, so every parameter including outDir, force, formats, framework, dtcgDialect and packageName is already documented with defaults and enums. The description restates rather than extends: 'existing files are skipped unless force' mirrors the schema's force text, and the astro/Storybook caveat is already in the framework field. Baseline 3 applies.

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+resource (generate the design-system package skeleton at outDir) and enumerates exactly what is emitted: package.json with peer deps, src/components layout, token files, an MDX token-showcase page, and a README. It also carves out a boundary against the neighbouring figma_ds_setup_storybook concern by declaring 'Storybook itself is NOT installed by this tool', so an agent can distinguish it from siblings without opening the 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?

Prerequisites are explicit: it consumes the output of figma_ds_analyze and figma_ds_extract_tokens, and it is 'Local Mode only'. The post-step (run `npm create storybook@latest` inside outDir) is spelled out. It stops short of naming the sibling tools it competes with (e.g. figma_ds_setup_storybook, figma_ds_verify) or stating when not to scaffold.

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