Remove o fundo de uma imagem apontada por URL: recorta o objeto/pessoa em primeiro plano e devolve um link de download do resultado (PNG com fundo transparente por padrão), que também fica na aba Arquivos do mcp.ai. Opcionalmente troca o fundo por uma cor sólida (background) ou redimensiona (max_width). Leva poucos segundos. Um arquivo por chamada.
| Name | Required | Description | Default |
|---|---|---|---|
| format | No | ||
| image_url | Yes | ||
| max_width | No | ||
| background | No |
Changes observed during successful MCP inspections. Dates show when Glama detected each change.
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide no behavior hints (all false). The description adds behavioral details: it takes a few seconds, processes one file per call, and saves the result in the Files tab, which goes beyond the basic read/write annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is concise, well-structured, and front-loaded with the main action. It presents the output, optional modifications, timing, and limit in a logical flow without unnecessary fluff.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
It covers the core functionality, expected output, storage location, optional features, and operational constraints (time and file limit). This is sufficient for an LLM to understand when and how to invoke the tool correctly.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The description explains the `background` and `max_width` parameters and notes the default format (PNG). The `image_url` is self-explanatory, and the `format` enum is partially covered. This adds meaning beyond the bare schema, though not all enumeration values are specified.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's purpose: removing the background from an image given by URL, and distinguishes it from sibling tools like authenticate or report_bug, which are unrelated.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It provides usage context by specifying the input (image URL), output (download link, saved in Files tab), and optional parameters (background color, max_width). Though it doesn't explicitly mention alternatives, there are no competing image-processing tools among the siblings, so the guidance is sufficient.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
The set mixes one domain-specific tool with several overlapping platform utilities. marketplace duplicates report_bug, while connect, authenticate, and toolkit_info all touch connection/auth status, making it unclear which tool an agent should call first.
Names are readable and all lowercase snake_case, but they do not follow one pattern: authenticate and connect are bare verbs, marketplace and toolkit_info are nouns, and removebg_remove is a brand-style imperative. The inconsistency is noticeable but not chaotic.
Seven tools is a reasonable raw count, but the server's scope is unfocused: only one tool actually performs the 'Remover Fundo' domain work, while the rest are platform meta-tools, and marketplace alone bundles many subactions. It is slightly more than needed for the stated purpose.
The core background-removal flow works for URL-hosted images with basic options, but the server lacks local-file input, batch processing, richer output controls, and a clear remove.bg-specific configuration surface. The platform side is fairly complete, but the domain side has notable gaps.