Skip to main content
Glama

Remove or Fill Masked Area

sirv_remove_object

Remove logos, people, reflections, or dust from an image by masking the area, or fill that masked region using a text prompt. Returns a new result URL without altering the source.

Instructions

Remove what a mask covers in one image, or fill that area from prompt. White areas in the mask image at mask_url mark what to change.

Use it to remove a logo, a person, a reflection or dust. For an edit without a mask, use sirv_edit_image.

The source image does not change. Returns the result URL.

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>",
      "mask_url": "<mask_url>"
    },
    "name": "sirv_remove_object"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptNoWhat fills the masked area, up to 1000 characters. Without it, the tool removes what the mask covers
mask_urlYesPublic URL of a black and white mask image, the same size as the image. White marks the area to change
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?

Beyond the annotations it discloses the two facts that matter most for a mutation tool: the source image is not modified and the call returns a result URL. It also warns that workspace credits are spent. Minor gap: it says cost depends on 'the model and options', but no such parameters exist in the schema, which could puzzle an agent.

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?

Three short blocks, front-loaded with the core action, followed by use cases, then behavioral caveats. No filler and every sentence carries decision-relevant information.

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 three-parameter tool with no output schema, the definition covers what it does, what the mask means, what the source image fate is, what it returns, and what it costs — the full set of facts an agent needs to call 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 coverage is 100%, so all three parameters are already documented with formats, length bounds, and mask polarity. The description restates the white-marks-the-area rule and the prompt-absent behavior consistently but adds no syntax or format detail beyond the schema; baseline 3 applies.

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 — remove or fill the region a mask covers in a single image — and immediately contrasts it with sirv_edit_image for maskless edits, so the agent can differentiate without reading either 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 both positive examples ('remove a logo, a person, a reflection or dust') and an explicit routing rule to an alternative ('For an edit without a mask, use sirv_edit_image'), which is the exact when-vs-when-else information needed for selection.

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