ui_layout_audit

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

With no annotations provided, the description carries the full burden. It discloses key behavioral aspects: it uses accessibility frames, accounts for hitSlop, checks horizontal overflow, and explicitly contrasts itself with visual inspection ('Arithmetic, not eyeballing a screenshot'). It could add more detail about the return format or prerequisites, but it is transparent about its non-visual, analytical nature.

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 extremely concise—two sentences that immediately convey the tool's purpose, the specific checks performed, and its key differentiator (arithmetic vs. visual). Every word earns its place, with no fluff or repetition.

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?

For a relatively simple tool with two optional parameters and no output schema, the description provides sufficient context for an agent to understand what the tool does. It covers the input semantics and the nature of the audit. However, it does not describe the output format (e.g., list of violations, report style), which is a minor gap given that no output schema is present.

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?

The schema already provides complete descriptions for both parameters (screenWidth and minTapTarget), achieving 100% coverage. The tool description references these concepts (horizontal overflow, minimum tap target, hitSlop) but does not add new semantic information beyond what the schema already states. The baseline of 3 is appropriate, as the description merely reinforces the schema rather than enhancing it.

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's function with a specific verb ('Audit') and resource ('screen geometry from accessibility frames'), listing concrete checks (zero-size elements, tap targets under minimum after hitSlop, horizontal overflow). This distinguishes it from siblings like 'ui_check_alignment' and 'snapshot_ui', making its purpose unmistakable.

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 clear usage context by specifying that the tool performs arithmetic-based auditing rather than visual screenshot inspection, implicitly directing users to choose it when precise geometric verification is needed. However, it does not explicitly mention alternatives or situations where other tools should be used instead.

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