Skip to main content
Glama

compose

Translate natural language design tasks into multi-step plans that classify intent, build execution steps, and run them automatically.

Instructions

Run the agent orchestrator with a natural language design intent — classifies the task, builds a multi-step plan, and executes it.

Prerequisites: No Figma connection required for spec/code tasks. Figma-touching tasks (design generation, audits) require the bridge to be running. The orchestrator automatically dispatches to registered agent workers when available, or falls back to internal execution.

Returns on success: Orchestrator result object with shape { success: boolean, plan: { steps: [] }, results: [], summary: string, errors?: [] }. Each step includes the agent role that handled it and its output.

Error behavior: Returns success=false with an errors array if planning fails or execution throws. Individual step failures are captured per-step and do not abort the entire plan.

Intent examples:

  • "create a dashboard page with KPI cards, a chart, and a data table" — generates specs and code

  • "audit button variants for WCAG contrast and touch target compliance" — runs accessibility checks

  • "generate a login page with email/password form and OAuth buttons" — spec + codegen

  • "pull design system, then generate all missing component specs" — chained multi-step pipeline

  • "create a molecule spec for a search bar composing Input and Button atoms" — atomic design authoring

Be specific — vague intents like "make something nice" produce generic plans. Include component names, atomic levels, and target pages when relevant.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
intentYesNatural language design task. Be specific about what to create, modify, or check. Include atomic level if relevant (atom/molecule/organism/template/page), component names, and target output (spec, code, audit). Examples: 'create a KPI card atom with value, label, and trend props', 'audit all organism specs for WCAG 2.2 compliance', 'generate the LoginPage template from the AuthForm organism spec'.
dryRunNoIf true, returns the execution plan without running any steps. Use to inspect what the orchestrator intends to do before committing. Defaults to false.
Behavior4/5

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

No annotations provided, so description carries full burden. Discloses success/error shapes, step failure handling (non-aborting), and fallback execution. Could add more on rate limits or auth needs but sufficient.

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?

Well-structured with clear sections (prerequisites, returns, errors, examples). Every sentence adds value, no fluff.

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?

Given no output schema or annotations, description covers input, behavior, error behavior, and examples comprehensively. Suitable for a complex orchestrator tool.

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 covers 100% of parameters with descriptions. Description adds value with intent examples and clarifies dryRun behavior (inspect plan before committing).

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 runs an agent orchestrator with natural language design intent, builds multi-step plans, and executes them. It distinguishes from sibling tools like design_doc or generate_code by being a higher-level orchestrator that dispatches to workers.

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?

Prerequisites (Figma bridge requirement for design tasks) and failure handling are explained. Provides multiple intent examples but lacks explicit when-not-to-use scenarios.

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/sarveshsea/memi'

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