Skip to main content
Glama

Remove objects

erase_objects

Remove objects from a photo by describing them, for example "the cables on the desk" or "the person on the left". The rest of the image is kept pixel for pixel. Costs 25 credits (enhance 40, paid credits).

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": "erase_objects"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoOutput format. png keeps transparency everywhere; webp is smaller; jpg has no transparency.
promptYesWhat to remove, in plain words.
qualityNofast (default) or enhance for harder scenes.
image_urlNoPublic http(s) URL of a JPG, PNG or WebP image (up to 25 MB).
image_base64NoThe image as base64 (or a data: URL), if there is no public URL. Prefer image_url for large files.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Adds real context beyond the annotations: non-target pixels are preserved exactly, and the operation costs 25 credits (40 for enhance). This is exactly the kind of cost/side-effect information the annotations (which only say non-readonly, non-idempotent, non-destructive) cannot convey. It stops short of describing permissions, failure modes, or the return value.

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?

Two sentences, zero filler — the capability and its concrete invocation shape come first, with the preservation guarantee and price front-loaded after. Nothing repeats the schema or the title.

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 five parameters fully documented in schema and no output schema, the description covers the main gaps: prompt phrasing, cost, and edit scope. The notable omission is what the call returns (an image URL/bytes?) and whether credits are charged on failure — relevant for a paid, non-idempotent operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3; the description still adds meaning by tying the 'enhance' value to an elevated price and by showing the style of prompt the free-text parameter expects. It does not clarify image_url vs image_base64 tradeoffs, but the schema already does.

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?

States a specific verb and resource ('Remove objects from a photo by describing them') and backs it with two concrete prompt examples, so the agent knows the mechanism is prompt-driven object removal. It does not name or distinguish itself from the sibling remove_background, leaving that boundary implicit.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is only implied by the examples — the agent can infer that this is for object-level erasure rather than whole-background removal, but no when-to-use/when-not guidance or alternative is stated. The fast-vs-enhance choice is left entirely to the schema.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.