Skip to main content
Glama

Edit Image

sirv_edit_image

Edit an existing image from a text prompt to change its colour, style or setting while keeping the original file intact. Returns a URL for the new, edited image.

Instructions

Change one image with a text prompt, for example its colour, style or setting.

Use it for free-form edits. For a new background, use sirv_replace_background. To remove or fill a masked area, use sirv_remove_object. To translate the text in an image, use sirv_translate_image_text.

Inputs: image_url and prompt are required. strength, 0 to 1 (default 0.75), sets how far the result may move from the source. model defaults to nano-banana-lite-edit.

The source image does not change. Returns result_url, the edited 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": {
      "image_url": "<image_url>",
      "prompt": "<prompt>"
    },
    "name": "sirv_edit_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoEdit model. Default: nano-banana-lite-editnano-banana-lite-edit
promptYesThe change to make, in words, up to 2000 characters
strengthNoHow far the result may move from the source, 0 to 1. Higher changes more. Default: 0.75
image_urlYesPublic URL of the image to edit

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A4.5/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, destructiveHint=false, openWorldHint=true and idempotentHint=false; the description adds genuinely new context on top: the source image is not modified, the call spends workspace credits with model-dependent cost, and the output is a result_url. It stops short of covering failure modes, credit amounts, or turnaround, so it is strong rather than exhaustive.

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, then alternatives, then inputs, then side effects and cost — each in its own short block. No sentence is wasted, and the paragraph break structure maps to the agent's decision sequence.

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 4-parameter, non-destructive generation tool with no output schema, the description covers purpose, alternatives, required inputs, key defaults, side effects (credits, unchanged source) and the return value (result_url). Nothing an agent needs in order to call 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 every parameter is already documented, including the strength range and the model default. The description restates the required inputs and repeats the strength range/default and the model default rather than adding new meaning such as how strength interacts with specific models. Baseline 3 is appropriate when the schema carries the semantics.

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 specific verb and resource ('Change one image with a text prompt') and immediately scopes it to free-form edits such as colour, style or setting. It explicitly names the sibling tools that handle adjacent tasks (sirv_replace_background, sirv_remove_object, sirv_translate_image_text), so an agent can distinguish it without opening any schema.

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?

Gives a positive selection rule ('Use it for free-form edits') plus three explicit exclusion-and-routing rules for background replacement, masked removal/fill, and text translation. This is exactly the when-to-use/when-not pattern that lets an agent choose between near-neighbour tools.

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