analyze_design

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

No annotations are provided, so the description carries full responsibility. It comprehensively documents prerequisites (Figma bridge, ANTHROPIC_API_KEY), error conditions (missing key, invalid node, missing spec), and return shapes for all three modes with detailed fields. This level of disclosure fully equips the agent to anticipate outcomes.

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 relatively long but well-organized into logical sections (Prerequisites, Returns, Error behavior, Mode selection guide, Best-use context). Every sentence serves a purpose—there is no redundant or filler content. Front-loading the core action ('Capture...analyze') is effective. Slightly longer than ideal, but structure justifies it.

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 complexity (multiple modes, dependencies, error paths), the description covers all critical aspects: prerequisites, mode-specific outputs, error behavior, and usage context. There is no output schema, so the description must detail return values, which it does thoroughly for each mode. No gaps remain.

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?

Although schema description coverage is 100%, the description adds meaningful context beyond the schema: e.g., 'Omit to capture the entire current page' for nodeId, and elaborates on mode behaviors in the selection guide. The schema itself is clear, but the description enriches with operational hints (e.g., 'Obtain IDs from get_selection or get_page_tree').

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 starts with a clear verb+resource combination: 'Capture a Figma node as a screenshot and analyze it with AI vision (Claude).' It further distinguishes three distinct analysis modes (general, accessibility, spec-compliance), making it unique among siblings like capture_screenshot (capture only) or plan_ui_fixes (fix planning).

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?

Includes a dedicated 'Mode selection guide' with explicit scenarios for each mode (e.g., 'Use to verify that what's in Figma matches what's in the spec before generating code'). It also mentions the tool's place in a 'self-heal loop' and lists prerequisites. However, it stops short of explicitly saying when NOT to use the tool or naming direct sibling alternatives beyond capture_screenshot.

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