get_variable_defs

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

With no annotations, the description carries the full burden, and it delivers a stated output contract: a map of variable names to resolved values with an example. It also clarifies the scope ('referenced by a node'), though it does not mention auth prerequisites, empty results, or failure modes.

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?

Three short labeled sentences each carry distinct information: behavior, output format, and use case. No filler or redundant restatement, and the key action is front-loaded.

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 two-parameter read operation with no output schema, the description gives enough to invoke it correctly: what it takes, what it returns, and when to use it. It lacks only edge-case or auth details, which are non-critical for this simple call.

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%: both required parameters, fileKey and nodeId, already have descriptions with patterns and examples. The tool description adds no parameter-specific semantics, so the 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?

The description opens with a precise verb-resource pair: 'Returns all design variables (tokens) referenced by a node', listing concrete categories (colors, spacing, typography) and the output shape. This makes it clearly distinguishable from sibling tools like get_metadata and get_screenshot, which target different resources.

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 last sentence gives an explicit intended use case: 'Use to extract the design system token palette before writing code or creating new nodes.' This is clear context, though it does not state alternatives or exclusion conditions relative to tools like get_design_context.

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