Skip to main content
Glama

Generate Image

sirv_generate_image

Create 1–4 new images from a text prompt when no source image exists; choose the model, aspect ratio, and image count.

Instructions

Generate 1 to 4 new images from a text prompt.

Use it when there is no source image. Do not use it to change an existing image (use sirv_edit_image) or to put a real product into a scene (use sirv_place_product_in_scene).

Inputs: prompt is required. model defaults to nano-banana-2-lite, aspect_ratio to 1:1 and num_images to 1.

Returns result_urls, one URL for each image.

Credits: spends workspace credits. The cost depends on the model and options.

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": {
      "prompt": "<prompt>"
    },
    "name": "sirv_generate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoImage model. Default: nano-banana-2-litenano-banana-2-lite
promptYesThe image to make, in words, up to 2000 characters
num_imagesNoHow many images to make, 1 to 4. Default: 1
aspect_ratioNoWidth to height of the images. Default: 1:11:1

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare this is a non-read-only, non-destructive, non-idempotent, closed-world write. The description adds context those annotations cannot carry: it spends workspace credits, cost varies by model and options, and it returns one URL per image. It stops short of saying whether generated images are persisted to the asset library or how long URLs live.

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?

Purpose comes first, then routing guidance, then inputs, returns, and cost — each as a short scannable line. No sentence is redundant and all the decisive information is front-loaded.

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

Completeness4/5

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

With no output schema, the description responsibly names the return value (result_urls) and covers cost, defaults, and routing for a four-parameter tool. Minor gaps remain around whether results are persisted assets or whether generation is synchronous, but nothing critical for invocation is missing.

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 parameter already has documented meaning, enum values, and defaults. The description only restates the defaults for model, aspect_ratio, and num_images and marks prompt as required, adding no new semantics beyond the schema. Baseline 3 is appropriate here.

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 first line states a specific verb and resource with scope: 'Generate 1 to 4 new images from a text prompt.' The following line explicitly separates it from sirv_edit_image and sirv_place_product_in_scene, so an agent can route correctly without opening sibling schemas.

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?

It gives both a positive condition ('when there is no source image') and two named exclusions with the alternative tool to use instead. That is the full when/when-not/alternatives pattern, leaving nothing to inference.

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