Skip to main content
Glama

Generate an image with Antigravity

antigravity_image

Generates an image from a text prompt with Gemini on your AI Pro quota, saves it, and returns its absolute path, real format, and byte size for viewing.

Instructions

Your only image generator: makes an image with Gemini (agy CLI) on the user's AI Pro quota, saves it, and returns its absolute path, real format and byte size (read the path to view it). agy picks the format, so the extension is corrected to the bytes (out.png may come back as out.jpg). Relative paths land in workspace. For several images, use antigravity_image_swarm. Runs an unsandboxed agy session: trusted prompts only.

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": "antigravity_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
watchNoIf true, open the live "watch" window that streams agy's steps and shows the finished image inline (same return value, best-effort). Default false.
promptYesDescription of the image to generate.
timeout_sNoMax seconds to wait for agy to complete. Default 240 (image generation is slower than text).
workspaceNoWorking directory for the conversation. Defaults to cwd.
output_pathNoWhere to save. Absolute, or relative to `workspace`. If omitted, a timestamped name under `workspace` is used.

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.11.0

TDQS

A4.5/5.0
Behavior5/5

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

Anotations only declare readOnlyHint=false, openWorldHint=true, idempotentHint=false. The description adds materially: it consumes the user's AI Pro quota, runs an unsandboxed session that demands trusted prompts, corrects the file extension to match actual bytes, and places relative outputs under `workspace`. These are real operational and security facts the annotations do not carry.

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?

Front-loaded with the core action and return contract, then constraints, then the sibling pointer. Every clause carries information – the parenthetical about reading the path to view the image, the extension-correction warning, and the safety note all earn their place.

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?

For a five-parameter generation tool with a mutation profile, the description covers quota consumption, sandbox status, output location semantics and return values, plus a sibling for batching. With an output schema present, nothing an agent needs to invoke it correctly 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 the schema already explains prompt, watch, timeout_s, workspace and output_path. The description largely restates that ('Relative paths land in `workspace`') and adds only a marginal nuance about format/extension correction. Baseline 3 applies when the schema does the heavy lifting.

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?

States a concrete verb and resource ('makes an image with Gemini (agy CLI)'), the side effect ('saves it'), and the return shape ('absolute path, real format and byte size'). It also positions itself as 'your only image generator' and names the multi-image sibling, so an agent can distinguish it without opening a schema.

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?

Explicitly routes batch work elsewhere: 'For several images, use antigravity_image_swarm.' It also gives a usage constraint ('trusted prompts only') that tells the agent when this tool is inappropriate. It stops short of a full when/when-not matrix (e.g. guidance on choosing watch or timeout), so it is strong but not exhaustive.

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