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

Beyond the readOnly/idempotent/non-destructive annotations, the description adds meaningful behavioral context: screenshot pixels are not decoded for scoring, iOS secondaryLabel/tertiaryLabel are treated as platform-standard and produce warnings rather than failures, taste-profile bindings are unavailable on the hosted endpoint, and the return shape matches audit_page. These are non-obvious traits an agent needs 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?

The description is dense but every sentence earns its place: purpose, alias relation, no-arg behavior, concrete input shape, scoring dimensions, return shape, and endpoint limitation. It is front-loaded with the primary purpose and avoids redundant restatement of schema properties.

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 5-parameter tool with nested objects and no output schema, the description is remarkably complete. It tells the agent how to discover the snapshot shape, what the scoring covers, what the return shape is, and how to avoid project/profile complications. The optional screenshot's role is also clarified sufficiently.

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%, so the baseline is 3; the description adds extra meaning by showing the expected call shape, defining what the elements array is scored against (44×44pt targets, contrast, visual rhythm in points), and clarifying that omitting project/profile yields the stateless audit. This enriches the schema without needing to repeat every field definition.

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 a rendered iOS screen from a view-hierarchy/accessibility snapshot'. It further distinguishes itself by stating it is an alias of audit_screen with platform:"ios", and enumerates concrete checks (44×44pt touch targets, contrast, visual rhythm), which separates it from generic audit_screen and iOS-specific sibling 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 gives explicit invocation guidance: call with no arguments for the expected snapshot shape, call with the elements/viewport object to run the audit, and omit project/profile for a stateless run. It names audit_screen as the generic alternative, though it does not explicitly state when not to use audit_ios_screen versus related siblings like audit_ios_a11y or audit_ios_privacy.

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