Skip to main content
Glama

Standout

by io.standoutmcp
OverviewDiscussionsAdmin

get_design_direction

Get a complete, distinctive, reference-backed art direction for a website: palette with exact hex roles, type pairing, layout DNA, hero spec, component treatments, imagery rules, matched motion recipes, and public-product reference evidence. Use FIRST, before building, so the site has a coherent direction instead of defaults. The catalog holds 14 directions: 9 with light base palettes and 5 dark — pass tone to constrain. If you only know the business name, call it anyway: the response will give you a few quick questions to ask the user, then call again with their answers as vibe/audience. REDESIGNS: if the business has an existing website, pass its URL as current_site_url — Standout fetches it server-side and returns a content inventory (services, prices, hours, contacts) plus a redesign protocol, so no questions are needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
toneNoBase palette tone. Pass when the client asks for a light or dark site; matching stays inside that pool (9 light / 5 dark directions)
vibeNoDesired feel, e.g. premium, playful, technical, warm
audienceNoWho the site must convince
boldnessNoHow adventurous the signature concept should be: safe (conservative/trust-first businesses like clinics, accountants, law firms), elevated (default), bold, or experimental. A 'safe' request never receives a bold concept. Bold/experimental dials can unlock signature SET PIECES: finished interactive hero objects (drag-to-compare reveal, live pricing calculator, product console, scroll-driven process timeline) delivered as complete code by get_section_code.
businessNoWhat the business is, e.g. 'dive shop in Fiji running charters'. If omitted, the response returns a few quick intake questions to ask the user instead of erroring.
industryNoIndustry, e.g. restaurant, law firm, saas, gym
current_site_urlNoThe business's EXISTING website URL, for redesigns. Standout fetches it and returns the content to preserve + the redesign protocol

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / tone / description
      Previous value: -"Base palette tone. Pass when the client asks for a light or dark site; matching stays inside that pool (8 light / 4 dark directions)"New value: +"Base palette tone. Pass when the client asks for a light or dark site; matching stays inside that pool (9 light / 5 dark directions)"
  2. Changed1 schema field changed
    • changedInput schema / properties / boldness / description
      Previous value: -"How adventurous the signature concept should be: safe (conservative/trust-first businesses like clinics, accountants, law firms), elevated (default), bold, or experimental. A 'safe' request never receives a bold concept. Until round-2 primitives ship, higher dials still fall back to the strongest buildable concept instead of promising unbuildable interactions."New value: +"How adventurous the signature concept should be: safe (conservative/trust-first businesses like clinics, accountants, law firms), elevated (default), bold, or experimental. A 'safe' request never receives a bold concept. Bold/experimental dials can unlock signature SET PIECES: finished interactive hero objects (drag-to-compare reveal, live pricing calculator, product console, scroll-driven process timeline) delivered as complete code by get_section_code."
  3. Changed2 schema fields changed
    • addedInput schema / properties / boldness
      Added value: +{
+  "description": "How adventurous the signature concept should be: safe (conservative/trust-first businesses like clinics, accountants, law firms), elevated (default), bold, or experimental. A 'safe' request never receives a bold concept. Until round-2 primitives ship, higher dials still fall back to the strongest buildable concept instead of promising unbuildable interactions.",
+  "enum": [
+    "safe",
+    "elevated",
+    "bold",
+    "experimental"
+  ],
+  "type": "string"
+}
    • removedInput schema / properties / current_site_url / format
      Removed value: -"uri"
  4. Changed3 schema fields changed
    • changedInput schema / properties / business / description
      Previous value: -"What the business is, e.g. 'dive shop in Fiji running charters'"New value: +"What the business is, e.g. 'dive shop in Fiji running charters'. If omitted, the response returns a few quick intake questions to ask the user instead of erroring."
    • removedInput schema / properties / business / minLength
      Removed value: -2
    • removedInput schema / required
      Removed value: -[
-  "business"
-]
  5. First observed

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly: it discloses the catalog size (14 directions, 9 light/5 dark), the behavior when business is omitted (returns intake questions), and the server-side fetching for redesigns. Edge cases are explicitly covered, making the tool's behavior predictable.

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 a single dense paragraph that front-loads the purpose and deliverables, then flows through usage, fallback, and redesign specifics. Every sentence adds useful information without redundancy, and the structure is easy to parse despite the density.

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?

The description covers the main success path, the minimal-info fallback, and the redesign workflow, all within a complex multi-parameter tool. It does not have an output schema, but it lists the response contents explicitly, providing enough detail for an agent to invoke and interpret the tool correctly.

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, but the description adds meaningful context beyond the schema: tone is tied to catalog counts, business omission triggers intake questions, and current_site_url triggers server-side fetch with content inventory. This enrichment lifts the score above baseline, though not all params get extra explanation.

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?

Clearly states the tool gets a complete, distinctive, reference-backed art direction for a website, enumerating specific deliverables like palette, type pairing, layout DNA, and more. This distinguishes it from sibling tools that focus on individual components (hero, motion, section code), making its role unmistakable.

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

Usage Guidelines5/5

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

Explicitly instructs to use FIRST, before building, and provides clear guidance for minimal-information scenarios (call anyway, ask questions) and redesigns (pass current_site_url). While it doesn't name alternative tools, it establishes precedence and gives concrete context for when to call it.

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

All Standout toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources