Skip to main content
Glama
DropBG AI Background Remover

DropBG AI Background Remover

Official

remove_background_batch

Batch-remove backgrounds from up to 10 local image files and save transparent or solid-color cutouts to disk.

Instructions

Remove backgrounds from multiple local image files sequentially (up to 10 files per batch) and save the cutouts to disk.

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": {
      "input_paths": "<input_paths>"
    },
    "name": "remove_background_batch"
  }
}

Input Schema

NameRequiredDescriptionDefault
formatNoOutput image format.auto
bg_colorNoOptional 6-digit hex background color (e.g. #FFFFFF).
defringeNoApply color decontamination on hair/fur edges.
output_dirNoOptional directory to write all processed cutouts into. Defaults to each input file's directory.
input_pathsYesList of local image file paths (max 10).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.4

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the burden and does add useful behavior: processing is sequential, capped at 10 files, and results are written to disk rather than returned inline. It omits important mutating-tool details such as overwrite behavior, what happens when some files fail mid-batch, and whether output paths are reported back.

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?

A single front-loaded sentence with no filler: verb, resource, processing mode, batch limit, and output destination. Nothing is repeated and nothing extraneous is included.

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

Completeness3/5

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

For a 5-parameter mutation tool with no annotations and no output schema, the description covers what is processed and where results land but not what the tool returns or how partial failures are handled. An agent can call it, but cannot predict the response or error semantics.

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 format, bg_color, defringe, output_dir and input_paths are already documented. The description only reinforces the input_paths limit ('up to 10 files per batch') and the disk-write destination, adding little beyond the schema; baseline 3 applies.

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 backgrounds from local image files), plus scope (multiple files, sequential, max 10) and outcome (cutouts saved to disk). It implicitly separates itself from a single-file or URL variant by emphasizing 'multiple local image files', but never names the siblings, so differentiation is inferred rather than stated.

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 implied by 'multiple local image files' and the 10-file cap, which tells an agent this is the batch path for local inputs. There is no explicit when-to-use versus remove_background_file/remove_background_url, and no guidance on what to do for a single file or when the cap is exceeded.

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