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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description does not contradict these. It adds valuable context beyond annotations: specific checks performed (accessibilityLabel, hitSlop, allowFontScaling, etc.), what is rewarded, a limitation on taste-profile bindings on the hosted endpoint, and a pointer to audit_page for return shape. This is a solid disclosure without being overwhelming.

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 long but packs every sentence with distinct, useful information: scope, specific checks, exclusions, return-shape pointer, and hosted limitation. No filler or redundancy. It is denser than the mid-tier examples but not bloated for a tool of this complexity.

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 (5 params, no output schema), the description covers purpose, input types, exclusion boundaries, and behavioral limits. It leverages the sibling audit_page for return shape ('Same return shape as audit_page'), which is an efficient reference. It does not detail every return field, but that is acceptable given the pointer to a known sibling.

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 input schema already provides 100% parameter descriptions, so the description need not repeat them. It does add a meaningful semantic: omitting both project and profile yields a stateless audit, which clarifies the default behavior in a way the schema does not. This is a minor enhancement over the baseline, so a 3 is appropriate.

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 verb and resource: 'Audit React Native / Expo source (JSX/TSX + StyleSheet) against the iOS HIG + Android Material conventions RN must satisfy.' It further distinguishes from siblings by stating 'RN-native checks only — no web/CSS or SwiftUI rules' and explicitly contrasting with audit_ios_screen ('scores the rendered screen'). This makes the tool's purpose unambiguous.

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 clearly states what the tool is NOT for ('no web/CSS or SwiftUI rules') and directs users to audit_ios_screen for rendered screens, effectively providing an alternative. It also gives a practical usage tip: 'Omit project/profile to run the stateless React Native audit.' However, it does not explicitly enumerate sibling use cases beyond these two, so it stops short of full when-to-use guidance.

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