Editmamei Connect

editor_studio

Several editors on one photo (the side-by-side test): 2 to 4 editors, each on its own fresh copy of the photo, one after another. Start with source (what open_photo takes) and editors: it opens the first copy and hires its editor as plan_edit does. Work that copy as that editor, export it and close it, then call again with studio (the run's id) for the next copy. job, deliverable, subject and story apply to every copy. At the end review_edit with studio compares them all.

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": "editor_studio"
  }
}

Input Schema

Name	Required	Description
`job`	No
`story`	No
`source`	No	The photo, as open_photo takes it ("upload:<id>", a sample, or an https URL). To start a run.
`studio`	No	A run id: open the copy for its next editor.
`editors`	No	The editors, in order, each optionally with one of its styles. To start a run.
`subject`	No	[x1, y1, x2, y2] in image pixels.
`deliverable`	No

Schema Changelog

Changes observed during successful MCP inspections.

AddedNov 7, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations only say readOnly=false, destructive=false, idempotent=false, openWorld=true; the description adds the crucial behavior that each editor works on its own fresh copy, that each copy must be exported and closed before continuing, and that the tool is stateful across calls. That is real context beyond the annotations. It stops short of saying what happens if a copy is left open or whether the run expires.

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?

Four sentences, front-loaded with the identity of the tool before the procedural steps, and no filler. It is dense and slightly run-on with the parentheticals, but every clause carries information the agent needs to sequence the calls.

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 stateful multi-invocation tool with no output schema and partial schema coverage, this covers the call sequence, the shared-vs-start parameter split, and the ending review step. The one omission is that it never says the first call returns the `studio` id, which an agent must know to continue the run.

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

Parameters4/5

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

With 57% schema coverage, the description compensates by splitting parameters into two roles: `source`/`editors` are start-only, while `job`, `deliverable`, `subject` and `story` apply to every copy. It also clarifies that `studio` is the handle for resuming the run, which the schema alone states only terseley. It does not explain what `story` or `deliverable` actually mean, though those are likely inherited from open_photo/plan_edit.

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?

"Several editors on one photo (the side-by-side test): 2 to 4 editors, each on its own fresh copy" states a specific verb, resource and cardinality, and the parenthetical names the exact capability that distinguishes it from plan_edit and batch. An agent can tell this apart from all 50+ siblings without opening the schema.

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?

It gives an unusually explicit two-phase invocation contract: start with `source` + `editors`, then re-call with `studio` for the next copy, and finish with review_edit. It also names the related siblings (open_photo, plan_edit, review_edit) as workflow partners. The only gap is that it never states when NOT to use this (e.g. a single editor, or many photos), leaving the 2-4 editor boundary implicit.

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

All Editmamei Connect tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?