figma-mcp-go

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

Annotations declare destructiveHint=true; description confirms 'save to local filesystem'. Adds crucial behavioral detail not in annotations: 'Returns metadata only (no base64)'. Missing: idempotency details (annotations say false) or overwrite behavior.

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?

Two sentences total. First establishes action and target; second clarifies return format. Zero redundancy—every clause adds distinct value (filesystem persistence vs base64 return distinction).

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?

Good coverage for core functionality given comprehensive schema and annotations. Minor gap: doesn't specify file path handling (absolute vs relative, auto-created directories, overwrite behavior) which is relevant for destructive filesystem operations.

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 baseline 3 is appropriate. Description references 'multiple nodes' mapping to items array, but doesn't add syntax/format details beyond what schema already documents for format, scale, and nested item properties.

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?

Clear specific verb ('Export') + resource ('screenshots for multiple nodes') + scope ('local filesystem'). Distinguishes from sibling 'get_screenshot' by emphasizing file system persistence rather than data return.

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?

Implies usage context via 'Returns metadata only (no base64)'—suggesting when to use vs get_screenshot. However, lacks explicit 'when to use' statement comparing to export_frames_to_pdf or other export tools.

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