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

Annotations already declare readOnly/idempotent/non-destructive behavior, so the bar is lower. The description adds what is analyzed, but it does not disclose the output/response format, error behavior, or any caveats about required color/contrast inputs; with no output schema the return shape is unstated.

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 the core purpose and an efficient em-dash list of checks; the input shape is stated compactly. No filler or redundant phrasing.

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?

The tool has nested inputs and no output schema, and the description covers input enough to invoke, but it leaves the return value unspecified and fails to mention the minTarget option. For a scoring tool without an output schema, a bit more output/options context would be needed for full agent autonomy.

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?

With schema_description_coverage of 0%, the description must compensate. It names the required elements structure and viewport and gives purpose to fields (e.g., rect for tap targets, fgColor/bgColor for contrast), but it omits the optional options.minTarget parameter entirely and does not explain parameter value semantics beyond repeating property names.

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 opens with a specific action ('Score an accessibility-enriched iOS element snapshot') and enumerates the exact checks (labels/values/traits, tap targets, WCAG contrast, Dynamic Type clipping, VoiceOver order), clearly distinguishing it from narrower sibling audits like audit_contrast or audit_tap_targets.

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?

It indicates the tool applies to iOS accessibility snapshots produced by the AccessibilitySnapshot XCUITest/ios-capture harness, giving clear context for when to invoke it. It does not explicitly name alternatives or say 'do not use for other snapshot types,' but the iOS/XCUITest framing is enough to imply the intended scope.

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