Skip to main content
Glama

page.analyze

Read-onlyIdempotent

Analyze web pages by detecting layout structure, extracting motion patterns, and evaluating quality in parallel for unified results.

Instructions

Analyze a web page URL with layout detection, motion pattern extraction, and quality evaluation. Executes layout.ingest, motion.detect, and quality.evaluate in parallel and returns unified results. Supports MCP streaming progress via _meta.progressToken for real-time phase notifications.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesTarget URL to analyze (required)
asyncNoAsync mode (default: auto). true: enqueue a BullMQ job and return a jobId immediately (poll with page.getJobStatus). false: synchronous processing. When omitted, auto-enabled if Vision is on and Redis is available (Vision LLM exceeds the MCP timeout in CPU mode). Requires Redis when true.
summaryNoReturn summary response (default: true). Set to false for full details.
timeoutNoOverall timeout in ms (default: 600000)
featuresNoFeature flags for analysis (default: all true)
waitUntilNoPage load completion criteria (default: networkidle)networkidle
auto_retryNoEnable staged auto-retry on HTML fetch failure (default: true). Retries with progressively longer timeouts and relaxed waitUntil.
sourceTypeNoSource type: award_gallery or user_provided (default)user_provided
usageScopeNoUsage scope: inspiration_only (default) or owned_assetinspiration_only
max_retriesNoMaximum retry attempts when auto_retry is true (default: 3).
auto_timeoutNoEnable Pre-flight Probe for dynamic timeout calculation (v0.1.0). Analyzes page complexity (WebGL, SPA, heavy frameworks) before analysis and calculates optimal timeout. Results are included in preflightProbe response field.
layout_firstNoLayout-first mode for WebGL/Three.js sites (default: auto). auto: prioritise layout when WebGL is detected. always: always prioritise layout. never: legacy parallel processing.auto
auto_snapshotNoAuto-save design snapshot after analysis (default: false). Creates a point-in-time record for design.track_changes comparison.
layoutOptionsNoLayout analysis options
layoutTimeoutNoPer-phase timeout for layout analysis in ms (default: 120000).
motionOptionsNoMotion detection options
motionTimeoutNoPer-phase timeout for motion detection in ms (default: 300000).
visionOptionsNoVision CPU completion-guarantee options (Phase 3). Controls Vision model (Ollama llama3.2-vision) inference timeout, image optimisation, CPU forcing, and graceful degradation.
qualityOptionsNoQuality evaluation options
qualityTimeoutNoPer-phase timeout for quality evaluation in ms (default: 60000).
partial_resultsNoAllow partial results on timeout (default: true). When true, returns results from completed phases on timeout.
narrativeOptionsNoNarrative analysis options. Analyzes the page's worldview/atmosphere and layout structure. enabled=true to activate.
timeout_strategyNoTimeout strategy. strict: fail completely on timeout. progressive: return partial results on timeout (default).progressive
responsiveOptionsNoResponsive layout analysis options. Captures layouts at multiple viewport sizes (desktop/tablet/mobile) and detects differences in typography, spacing, navigation, and layout structure.
performanceOptionsNoPerformance evaluation options (v0.3.0 Phase 7.5b, opt-in). Core Web Vitals (LCP/FID/CLS/INP/TTFB) measurement. Timeout: 40s. Disabled by default.
respect_robots_txtNoRespect robots.txt (RFC 9309). Set to false to ignore.
accessibilityOptionsNoAccessibility audit options (v0.3.0 Phase 7.5a, opt-in). WCAG 2.1 AA compliance audit via axe-core. Timeout: 10s. Disabled by default.
Behavior4/5

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

Aligns with annotations (readOnlyHint, openWorldHint, idempotentHint). Adds behavioral details: parallel execution, MCP streaming progress, async mode, timeouts. No contradictions.

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?

Extremely concise with no wasted words. Two sentences cover purpose, execution model, and streaming support.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with 27 parameters, nested objects, and no output schema, the description is too brief. It lacks return value description, error handling, and guidance on interpreting results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds minimal extra meaning beyond the schema, such as explaining the three phases that the 'features' parameter controls.

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 clearly states the tool's verb 'Analyze', the resource 'web page URL', and the three main analysis phases (layout, motion, quality). It also differentiates itself from sibling tools like layout.ingest and motion.detect by being a unified parallel execution.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use page.analyze versus calling the individual sub-tools directly. Missing when-not-to-use or alternatives for partial analyses.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/TKMD/ReftrixMCP'

If you have feedback or need assistance with the MCP directory API, please join our Discord server