figma_ds_verify

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

With no annotations, the description carries the burden well: it discloses that checks are deterministic gates, that each encodes a real failure class, that it reports Figma round-trip readiness, and that it is Local Mode only. It does not describe the return/report shape, which is a minor gap given no output schema.

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 core purpose, then dense specifics (DTCG parsing, alias resolution, var() consumption, stories/barrels). Slightly long due to the enumerated checks, but each clause conveys a concrete failure class rather than filler.

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 annotations and no output schema, the description is thorough about inputs and checks and flags the Figma round-trip / code-led-vs-design-led decision. Only the report/return format is left unspecified.

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?

Only one parameter at 100% schema coverage, so the schema documents it. The description adds meaning by stating it must be the same outDir used in figma_ds_analyze, tying the parameter to a sibling's output.

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 ('Run deterministic fidelity evals') on a specific resource ('extracted design system package') and enumerates exactly what the checks verify. Clearly distinguishes it from siblings like figma_ds_analyze (extraction) and figma_ds_status.

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 clear context: it is the 'governance gate before handing off or pushing to Figma' and is 'Local Mode only.' It implicitly follows figma_ds_analyze by matching outDir, but does not explicitly name when to prefer figma_ds_status vs this verify step.

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