Export / screenshot a node

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

Annotations only carry the read-only/safe profile, but the description adds substantial behavioral detail beyond them: the ≤5 MB inline threshold, the 1024 px inline cap, the `capped` signal, cross-parameter defaults (format vs saveTo extension), and the BRIDGE_EXPORT_ROOTS requirement for write locations. This is rich disclosure about side effects and limits that the annotations do not cover.

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, and nearly every clause adds functional information. It is a dense single paragraph with many parenthetical asides, which is slightly heavy to scan, but it avoids padding and repetition.

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?

Despite no output schema, the description explains what comes back in each mode (inline image with bounds and pixel size, SVG markup, or a written file path). Combined with the coverage of defaults, limits, and path rules, an agent has everything needed to invoke it correctly.

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%, so the schema already documents all six parameters (baseline 3). The description goes further by explaining cross-parameter interactions the schema cannot: scale bypassing the size cap, format being inferred from the saveTo extension when omitted, relative saveTo destinations, and nodeId defaulting to the selected layer.

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 ('Render a node') plus the intent ('so you can see it — the screenshot to compare against'), making the purpose immediately actionable. It also distinguishes itself from siblings by name (figma_export_video for motion, figma_download_assets for shipped files), so an agent can route without opening a 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?

Explicit when-to-use vs alternatives: animated frames render at rest, so use figma_export_video then figma_review_video for motion; for files a codebase ships use figma_download_assets. It also names the relevant skill (critique via figma_get_guide). Nothing is left to inference.

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