Skip to main content
Glama

Raven

by ai.ravenmcp

audit_ios_screen

Read-onlyIdempotent

Audit a rendered iOS screen from a view-hierarchy/accessibility snapshot (and optional screenshot). Alias of audit_screen with platform:"ios". Call with no arguments for the expected snapshot shape. Call with {elements:[{label,rect:{x,y,w,h},role,fontPt,fgColor,bgColor}],viewport:{w,h}} to score 44×44pt touch targets, contrast (with iOS secondaryLabel/tertiaryLabel treated as platform-standard — warn not fail), and visual rhythm (alignment, gap consistency, optical balance) in points. Same return shape as audit_page. Taste-profile bindings are not available on the hosted (remote) endpoint (per-user state is a later phase). Omit 'project'/'profile' to run the stateless iOS screen audit.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
profileNoTaste profile owning the binding. Omit to search all stored profiles for one bound to the project.
projectNoProject identifier — resolves a saved taste surface binding (see bind_taste_surface). When the binding carries design_notes and a screenshot is passed, the screenshot's pixels verify the color-scheme notes; results gain note_assessments.
elementsNoElements captured from the rendered screen via an accessibility/view-hierarchy snapshot
viewportNoScreen size in pt (iOS) or dp (Android) at capture time, e.g. {w:393,h:852} iPhone 15, {w:412,h:915} Pixel
screenshotNoOptional base64 PNG of the screen, for the caller's reference. Geometry is scored from the snapshot, not decoded pixels.

TDQS

A4.7/5.0
Behavior5/5

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.

Conciseness5/5

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.

Completeness5/5

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.

Parameters4/5

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.

Purpose5/5

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.

Usage Guidelines4/5

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.

All Raven toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.7/5.0
Disambiguation4/5

Most tools have clearly distinct purposes (audit_* vs get_* vs list_* vs generate_* vs score_*), but there is notable overlap among audit_page, audit_layout, score_page, and audit_url (all audit rendered HTML, with audit_page and score_page explicitly sharing checks; audit_screen and audit_ios_screen are aliases). The get_* family (get_pattern vs get_content_pattern vs get_service_pattern, get_principles vs get_brand_principles vs get_content_principles) have overlapping boundaries that may cause misselection.

Naming Consistency4/5

Names follow a consistent verb_noun pattern (audit_*, get_*, list_*, generate_*, score_*, compose_*, suggest_*, search_*), which is predictable and readable. Minor deviations exist: 'evaluate_design' uses evaluate_ instead of audit_/score_, and 'process' isn't present but 'compose_system' uses compose_ instead of generate_/get_. Overall the convention is strong and consistent.

Tool Count2/5

45 tools is far beyond the typical well-scoped server (3-15 tools) and even beyond the 'heavy' 25+ threshold. The server appears to be an all-in-one design/UX knowledge base and auditing suite, but the sheer count makes discovery and selection overwhelming, and many tools (e.g., multiple audit_* variants for mobile platforms) could be consolidated.

Completeness3/5

The server covers a wide domain: audits for web/mobile/RN/SwiftUI, design tokens, UX principles, content systems, business strategy, creative scoring, and service design. However, there are gaps: no tool for creating or editing design systems (only get/generate), no update/delete operations anywhere (all read-only or audit-only), and the creative side has list/score but no generation tool. The set feels broad but shallow in lifecycle coverage.

Resources