Skip to main content
Glama

stitch_create

Create Stitch projects, screens, or design systems from resource payloads; use dry run to validate before making API calls.

Instructions

Creates one Stitch resource (project, screen, design-system). Mirrors 'stitch create '. Returns created resource metadata.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "resource": "<resource>",
      "body": "<body>"
    },
    "name": "stitch_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesResource payload. Required: project={title}, screen={prompt}, design-system={designSystem={displayName, theme}}.
dryRunNoValidate payload and preview without making API calls
projectNoStitch Canvas project ID
resourceYesResource type to create
workspaceNoWorkspace ID override

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.1

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full disclosure burden for a mutating tool. It establishes that a resource is created and that metadata is returned, but says nothing about required permissions or scope (project/workspace context), idempotency or duplicate handling, what happens on partial failure, or what the returned metadata contains.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the core action and the resource enumeration. The CLI-mirroring sentence is of marginal value but cheap, and nothing is padded or buried.

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

Completeness3/5

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

Five parameters with a nested payload object, no annotations, and no output schema make this a non-trivial tool; the description covers the what but not the operational how. Without an output schema, 'Returns created resource metadata' is a reasonable but thin substitute for describing the returned shape.

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 description coverage is 100%, and the schema itself documents the per-resource body requirements (project={title}, screen={prompt}, design-system={designSystem={displayName, theme}}) and the dryRun preview behavior. The description adds no parameter-level meaning beyond that baseline; only the resource-type list is echoed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb (creates) and resource family (Stitch resource), and explicitly enumerates the three accepted types: project, screen, design-system. It stops short of distinguishing this from likely overlapping siblings such as stitch_generate or stitch_resource, which an agent must resolve on its own.

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?

There is no statement of when to use this tool versus alternatives; the closest thing is 'Mirrors \'stitch create <resource>\'', which is a CLI mapping aid rather than guidance. No prerequisites, no exclusions, and no pointer to a sibling for preview or lookup cases.

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