Skip to main content
Glama

Upscale Image

sirv_upscale_image

Upscale small or soft product photos 2–4x with an AI upscaler to increase resolution while keeping the original source image unchanged.

Instructions

Make one image 2, 3 or 4 times larger with an AI upscaler.

Use it for small or soft product photos. Do not use it for a video (use sirv_upscale_video) or to change what the image shows (use sirv_edit_image).

Inputs: image_url is required. scale defaults to 2 and model to esrgan. prompt and creativity work with the clarity model only.

Studio also saves the result in the library as a new asset. The source image does not change. Returns 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>"
    },
    "name": "sirv_upscale_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoUpscaler: esrgan (fast, general), clarity (adds AI detail) or topaz (slower, keeps fine detail). Default: esrganesrgan
scaleNoHow many times larger: 2, 3 or 4. Default: 2
promptNoFor clarity only: what the image shows, to guide the added detail
image_urlYesPublic URL of the image to upscale
creativityNoFor clarity only: how much new detail to add, 0 to 1. Higher adds more

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.1

TDQS

A4.4/5.0
Behavior4/5

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

Beyond the annotations, the description discloses the key side effect: the result is saved to the library as a new asset while the source image is unchanged, which is what an agent needs to know before a non-idempotent write. It also discloses the return value (result_url) and that workspace credits are spent with model-dependent cost. The only gap is the absence of a concrete cost figure or error behavior, so it stops short of a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short, front-loaded paragraphs: what it does, when to use it, then inputs/side effects/cost. Every block is scannable and nothing is buried. Minor redundancy in restating the schema defaults and required image_url keeps it from a 5.

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 5-parameter mutation tool with no output schema, the description covers the operation, the required input, defaults, model-specific parameter constraints, the persistence side effect, the returned field, and the credit cost. An agent has everything needed to decide and call 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% and the schema already states defaults for scale and model and marks prompt/creativity as 'For clarity only'. The description repeats those facts ('scale defaults to 2 and model to esrgan', 'prompt and creativity work with the clarity model only') rather than adding new meaning, so it sits at the baseline for a fully documented schema.

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?

The first sentence names a specific verb and resource ('Make one image 2, 3 or 4 times larger with an AI upscaler'), including the exact scale range. It immediately distinguishes itself from the two nearest siblings by naming both 'sirv_upscale_video' and 'sirv_edit_image' with the condition that selects each.

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?

Explicit when-to-use ('small or soft product photos') and explicit when-not-to-use, each with a named alternative tool and the reason for routing there. There is no ambiguity about which tool handles video or content-changing edits.

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