design_diff

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

The description fully discloses behavioral traits: it writes a baseline file locally, never mutates Figma, never changes git. It also explains the different status returns. This adds significant context beyond the readOnlyHint annotation, which it aligns with.

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 lengthy but well-structured. The first sentence introduces the purpose, followed by workflow, parameter details, and file behavior. While it could be slightly more concise, the complexity of the tool justifies the length.

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 (3 parameters, no output schema, lifecycle of baseline/diff), the description is remarkably complete. It covers the entire workflow, default behaviors, file system impact, and even advises on version control. 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?

Schema coverage is 100% but the description adds meaningful context: nodeId defaults to selection, rootDir defaults to cwd, update:true overwrites the baseline. It also clarifies that nodeId can be a Figma URL. This goes beyond the basic schema descriptions.

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 it diffs a Figma node against a saved baseline, with a specific use case: 'so after a design changes you edit only the affected code instead of regenerating.' This distinguishes it from siblings like get_design_context (which just retrieves context) and other mutation tools.

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 explains the two-phase workflow: first call creates a baseline, later calls return diffs. It also covers the update parameter for accepting changes. While it doesn't explicitly state when not to use or mention alternatives, the context is clear enough for an agent to decide when to invoke this tool.

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