Skip to main content
Glama

stitch_generate

Triggers a backend generative job to create Stitch screens or variants from prompts, device, project, and creative-range settings, with optional dry-run validation.

Instructions

Triggers a backend generative creation job for Stitch screens or variants. Mirrors 'stitch generate '.

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>"
    },
    "name": "stitch_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNoNumber of variants to generate (1-5)
deviceNoDevice type: MOBILE, DESKTOP, TABLET, or AGNOSTIC
dryRunNoValidate arguments and preview without starting job
promptNoText prompt for screen or variant generation
aspectsNoTarget aspects for variants (LAYOUT, COLOR_SCHEME, TEXT_FONT)
projectNoStitch Canvas project ID
resourceYesResource type to generate
creativeRangeNoCreative range: REFINE, EXPLORE, or REIMAGINE

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv3.0.1

TDQS

B3.1/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden, and it does add one useful trait: the call 'triggers a backend job' rather than returning generated content directly. However, it never says whether the call blocks or returns a job handle, what the cost/latency profile is, what permissions or project scope are needed, or what the dryRun path actually does.

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?

Two short sentences with the core action front-loaded and no padding. The CLI-mirroring sentence is of marginal value and its '<resource>' placeholder is slightly vague, which keeps it from a 5.

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?

This is an eight-parameter generative mutation with no annotations and no output schema, yet the description says nothing about the interplay among prompt, aspects, device, count, and creativeRange, nor what a successful job returns. For a tool of this complexity, two sentences leave an agent under-informed about how to invoke it correctly.

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%, so every one of the eight parameters is already documented in the schema. The description adds no parameter meaning beyond the '<resource>' placeholder -- it says nothing about how aspects relates to variants, or when dryRun or creativeRange should be set. Baseline 3 is appropriate when the schema does all the work.

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 uses a specific verb and resource -- 'Triggers a backend generative creation job for Stitch screens or variants' -- which lets an agent separate it from generate_template, generate_motion_snippet, and generate_8state_component, since those target other artifacts. It stops short of a 5 because no sibling is named explicitly as the alternative route.

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 when-to-use or when-not-to-use guidance, and no conditions distinguishing this from the many other generate_* siblings. The second sentence maps the tool to a CLI command ('stitch generate <resource>'), which informs familiarity but does not tell an agent when this is the right choice.

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