figma_setup_design_tokens

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

With no annotations, the description carries the full burden and delivers real behavioral detail: alias resolution order (same-call first, then existing local variables, set-qualified stripping), partial-failure semantics (unresolvable references skip that value with a per-item warning while the batch still applies), and the Desktop Bridge prerequisite. Does not cover collection-name collision behavior or duplicate handling.

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-loads the primary action and scope, then layers in alias resolution and failure behavior. Dense but each clause (alias references, per-item warnings, plugin requirement) carries actionable information; minor verbosity in the parenthetical examples.

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 no-output-schema, 3-required-param bulk tool, the description covers scope, alias semantics, partial-success behavior, and the plugin prerequisite—enough to call it correctly. Missing only edge cases like existing-collection conflicts.

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% and the schema itself documents modes, token fields, and types richly, so baseline is 3. The description adds conceptual value by explaining the DTCG brace-reference/alias resolution mechanism that governs the 'values' object, going beyond a restatement of the schema.

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: 'Create a complete design token structure ... collection, modes, and all variables.' This clearly distinguishes it in scope from single-operation siblings, though it never names them (e.g., figma_batch_create_variables, figma_create_variable_collection) to nail the differentiation.

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 a concrete use case ('importing CSS custom properties or design tokens into Figma') and implicitly positions itself against 'raw figma_execute' for semantic collections. Lacks explicit when-not guidance or direct naming of the closest batch/create siblings.

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