Skip to main content
Glama

Run several steps on one image

run_pipeline

Run a multi-step workflow on an image in one call, for example remove the background, resize, convert and compress. Needs a Pro plan. Give "pipeline": { "steps": [{ "op", "params", "when"? }] } with ops remove_background, upscale, resize, crop, rotate, edit, watermark, convert, compress (params are the REST API's options, e.g. { "width": 1600 } or { "format": "webp", "mode": "smart" }; "when" makes a step conditional on format, min_width, max_width, min_bytes, max_bytes or has_alpha), or "preset": the name of a saved pipeline or a template (web-optimized, thumbnail, product-square, social-square, avatar, private-share). Set dry_run to see which steps would run and the resulting size without processing anything. Returns a download URL valid for one hour and a report of every step.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "run_pipeline"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNoThe source file's name, for the output name pattern.
presetNo
dry_runNo
versionNoA version of a saved pipeline. Default: the latest.
pipelineNoThe pipeline object. Use this or preset.
image_urlNoPublic http(s) address of the image. Use this or image_base64.
image_base64NoThe image file's bytes, base64-encoded. Use for a local file, e.g. one in the repository.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false and idempotentHint=false, so the mutation profile is covered. The description adds genuinely useful behavior beyond that: a Pro-plan requirement, the one-hour lifetime of the returned download URL, the per-step report, and the fact that dry_run computes size without processing. It doesn't say whether output artifacts persist or count against a quota, which is the main remaining gap.

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?

Front-loaded with the purpose and a motivating example, then moves to the payload shape and options in a logical order. It is dense and nearly every clause carries information, though the long parenthetical listing ops, params examples and 'when' keys is heavy to parse in one breath.

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 tool with no output schema and a nested free-form object, the description supplies everything needed to construct a call and interpret the result: accepted input forms, the two payload modes, the conditional-step vocabulary, and the return value (download URL plus step report) with its expiry. Nothing essential to correct invocation is missing.

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

Parameters5/5

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

The schema's most important parameter, 'pipeline', is an untyped object with additionalProperties:{} and no documentation, so the description carries the full burden — and it does: it gives the {steps:[{op, params, when?}]} shape, enumerates the nine valid ops, explains that params mirror the REST API options with examples, and lists the six 'when' condition keys. It also names the built-in presets and explains dry_run and preset-vs-pipeline exclusivity, far exceeding what the 71%-covered schema conveys.

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 specific verb and resource ('run a multi-step workflow on an image in one call') and immediately grounds it with a concrete example sequence (remove background, resize, convert, compress). This clearly distinguishes it from single-operation siblings like compress_image, convert_image, resize-style tools, and remove_background, which each do one of these steps.

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

Usage Guidelines4/5

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

Gives clear context for when to reach for it — chaining multiple operations in one call — and describes the dry_run preview path for when the agent wants to check before processing. It also states a prerequisite ('Needs a Pro plan'). It stops short of explicitly naming a sibling alternative (e.g. 'use compress_image for a single step'), so the when-not guidance is implied rather than stated.

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.

Resources