analyze_design

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

With no annotations provided, the description carries full burden. It discloses that the tool uses AI vision, requires prerequisites, and returns structured results per mode. It lists error conditions. It does not mention potential latency or side effects, but since the tool is non-destructive, this is acceptable.

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 three sentences: main action, prerequisites, then returns/context. It packs a lot of info efficiently but could be slightly more structured (e.g., bullet points). Still, it avoids unnecessary verbiage.

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 handling, and no output schema), the description is remarkably complete. It covers prerequisites, return formats per mode, error cases, and even places the tool in a 'self-heal loop' workflow. 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?

All three parameters are described in the schema with 100% coverage. The description adds context: explains mode options, how to obtain nodeId from sibling tools, and when specName is required. It even notes default behavior for nodeId (omitting captures whole page).

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 Figma node and analyzes it with AI vision for different modes (general, accessibility, spec-compliance). It distinguishes itself from siblings like 'audit_interface_craft' by focusing on AI-driven analysis, not just auditing. The self-heal loop context adds specificity.

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?

The description provides explicit prerequisites (bridge+plugin, API key, spec registry for spec-compliance) and explains when to use each mode. It mentions errors and required parameters per mode. However, it does not explicitly state when not to use this tool or compare to alternatives like 'audit_ux_tenets_traps'.

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