Skip to main content
Glama
eMCP for Evolution CMS

eMCP for Evolution CMS

Official

Job Create Tool

aimage.job.create

Starts an image job from a plain-language instruction to generate, edit, vary, or upscale one or more images, with planning and background execution.

Instructions

Start an AIMage job from a plain-language instruction: generate, edit, vary or upscale one or many images. A text model plans the work (enhancing prompts, asking questions when ambiguous, estimating cost); a background worker executes it. Poll with aimage.job.show; answer questions with aimage.job.reply; confirm costly plans with aimage.job.approve. Images on the person's own computer are fetched into the site first with amount.fetch (see amount.computers); results can also be sent to any aMount mount, a computer included, with deliver_to.

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": {
      "message": "<message>"
    },
    "name": "aimage.job.create"
  }
}

Input Schema

NameRequiredDescriptionDefault
sizeNoImage size control, e.g. 1024x1024
messageYesWhat to do, e.g. "generate 3 poster-style images of a red poppy field, 1024x1024, into rainbow/red" or "upscale every image in products/ 2x"
qualityNoQuality control
backgroundNoBackground control, e.g. transparent
deliver_toNoAlso send the results to this aMount mount: a name or uuid from amount.mounts, or a computer name from amount.computers such as "mypc"
text_modelNoPlanner model (default from settings); any chat model from aimage.models
image_modelNoImage model (default from settings)
aspect_ratioNoAspect ratio control
output_folderNoDestination folder relative to the images root
deliver_folderNoFolder there, e.g. "<shared folder>/photos/2025" on a computer

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.2.2

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only supply readOnlyHint=false; the description carries the real behavioral load. It discloses that the call is asynchronous (planner model proposes, background worker executes), that the planner may ask questions or estimate cost and that expensive plans require approval — significant consequences an agent could not infer from annotations alone.

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?

Three tight sentences: capability, execution model, then the sibling routing chain and delivery options. It is front-loaded with what the tool does, and the dense naming of siblings and gotchas all earns its place.

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?

For a 10-parameter asynchronous job tool with no output schema, the description covers planning, questions, cost approval, file ingestion and delivery destinations. It never states what the call returns (e.g. a job id to poll), though the mention of polling with aimage.job.show largely implies it.

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 names, types and examples for all 10 parameters are already documented. The description adds modest meaning: deliver_to can target a mount or a computer, and pre-existing local images must be fetched in first, but it gives no extra syntax or defaults beyond the schema. Baseline 3 is appropriate.

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 ("Start an AIMage job") plus the concrete instruction types it covers: generate, edit, vary, upscale, for one or many images. An agent can distinguish this entry point from the job follow-up siblings without opening any schema.

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?

Explicitly routes the agent through the lifecycle: poll with aimage.job.show, answer questions with aimage.job.reply, confirm costly plans with aimage.job.approve. It also names the prerequisites for local files (fetch into the site first via amount.fetch / amount.computers), leaving no ambiguity about which sibling to call next.

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