xd_audit_design

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

With no annotations the description carries the full burden, and it does reasonably well: 'background estimated' honestly flags a heuristic limitation, and it states what the response contains (findings with artboard/layer ids plus per-check totals). It stops short of declaring the operation read-only and says nothing about truncation behavior when maxPerCheck caps results, which an agent would want to know.

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, front-loaded with 'Design QA' and then the concrete check list, ending with the return shape. Every clause carries information; the enumeration is the substance of the tool, not padding.

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?

There is no output schema, so the description's closing sentence about findings, artboard/layer ids and per-check totals usefully fills that gap, and the estimated-background caveat sets expectations. Gaps remain around severity/prioritization of findings and the three undocumented threshold parameters.

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 only 40% — maxPerCheck, minFontSize and minTapTarget have no schema descriptions, only defaults and bounds. The description partially compensates by naming 'tiny text' and 'small tap targets' as checks, hinting at what those thresholds control, but it never says that these parameters tune the checks, and maxPerCheck is left entirely unaddressed.

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?

Names a specific operation ('Design QA') and then enumerates the exact checks it performs: contrast, tiny text, tap targets, placeholder text, duplicate colors, font/size proliferation, default layer names. That enumeration makes it unmistakable against siblings like xd_get_design_tokens or xd_find_layers, which retrieve rather than audit.

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 implies when to reach for it (you want a QA pass over a file or artboard) but never states it explicitly and offers no exclusions or alternatives. There is no guidance on when to prefer it over xd_get_design_tokens plus manual inspection, or on when a single-artboard audit is more appropriate than a whole-file one.

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