capture_screenshot

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

Despite no annotations, the description thoroughly discloses error behavior (throws 'Figma not connected' if plugin missing, bridge error for invalid node ID) and success return format (image block with type, data, mimeType). No contradictions present.

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?

Well-structured with clear sections: purpose, prerequisites, return format, error behavior, use cases. Each sentence adds value without redundancy. Front-loaded with main purpose, making it easy to scan quickly.

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?

Given the tool's moderate complexity (3 parameters, no output schema), the description covers all necessary context: prerequisites, parameter sourcing, format selection, error cases, and integration with sibling tools. No gaps identified.

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 covers all three parameters (nodeId, format, scale) with descriptions. Description adds practical usage guidance beyond schema: explains how to obtain node IDs from get_selection or get_page_tree, recommends scale values (1 for quick inspection, 2-3 for quality), and suggests when to use PNG vs SVG.

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 clearly states the tool captures a screenshot of a Figma node or entire page, returning image data. It specifically distinguishes between node-level and page-level capture, which differentiates it from sibling tools like analyze_design that use screenshots for analysis.

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?

Explicitly lists prerequisites (Figma bridge running, plugin connected) and directs to check_bridge_health for verification. Provides concrete use cases: visual inspection before/after mutations, first step in self-heal loop, feeding into analyze_design. Recommends SVG for vector components and PNG for complex frames.

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