Read a design as code

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

The annotations already mark the tool as read-only and non-destructive, and the description adds substantial behavioral context beyond that: images are inlined, icons are real SVG, batches are capped at 20, failures are isolated per entry, and there is no base64 in the response. This gives the agent a reliable model of how the tool behaves.

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?

The description is front-loaded with the core purpose and then moves into batch behavior and alternatives. It is longer than minimal, but nearly every sentence carries a distinct fact; only a small amount of redundancy exists between the formats discussion and the later png note.

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 read-only tool with 11 optional parameters and no output schema, the description provides the essential operational details: output formats, batch result shape, per-entry error handling, the 20-entry limit, and where to route image requests. Nothing an agent needs to choose or invoke this tool correctly is missing.

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?

The schema already documents all 11 parameters at 100% coverage, so the baseline is 3. The description adds meaningful behavior around those parameters, especially the {results:[…]} contract, the 20-entry cap, and the image/export distinction. It does not walk through every parameter, but it does not need to given the schema's completeness.

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 names a specific verb and resource: it extracts a Figma node into HTML, figmaCss, React, and CSS variants. It even frames itself as 'the tool that answers what does this design actually say,' making its role unmistakable against siblings like figma_export_png or figma_get_tree.

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?

It explicitly explains the batch input modes (nodeIds, urls, selection, saved) and when to prefer alternatives: 'ask figma_export_png for a picture, a node at a time.' It also clarifies that batches never return images, giving the agent a clear routing rule.

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