Tasvr

Isolate one specific thing from an uploaded photo into a reusable reference

isolate_reference_item

Cuts one thing (product, wardrobe-detail, jewelry, prop, background-element) out of an uploaded photo into a clean reference. Spends credits; returns a task id. The finished result carries isolatedReference {url, ref}. Added to the library only when saveToLibrary is true.

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": {
      "imageUrl": "<imageUrl>",
      "role": "<role>"
    },
    "name": "isolate_reference_item"
  }
}

Input Schema

Name	Required	Description
`role`	Yes	What to isolate — determines the exact isolation instruction used and which category the saved reference is filed under.
`label`	No	A short name for the saved reference, e.g. "Blue serum bottle".
`imageUrl`	Yes	A TASVR Storage URL — from upload_reference_image or list_reference_images.
`saveToLibrary`	No	Also keep the cutout in the human's reference library. Default false. Only set true after the human has said they want to keep it — ask them first.

Output Schema

Name	Required	Description	Default
`status`	Yes
`task_id`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Goes well beyond the annotations by disclosing credit consumption, that it returns a task id rather than a finished asset, that the result carries isolatedReference {url, ref}, and that library persistence is conditional. It does not say how to poll for the finished task or whether repeat calls create duplicate charges.

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 short sentences, front-loaded with the operation and its scope, then cost/async behavior, then the persistence condition. No filler sentences and nothing repeated between them.

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?

Covers the essential flow for an async, credit-spending mutation, and the output schema means return values need no elaboration. The notable gap is that it never points the agent to get_generation_status for retrieving the finished task, which matters for a tool that returns only an id.

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 role, label, imageUrl, and saveToLibrary are already fully documented including the enum values and the 'ask the human first' constraint. The description only restates the role list, adding no syntax or format detail beyond the 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?

States a concrete verb and resource — 'Cuts one thing ... out of an uploaded photo into a clean reference' — and enumerates the eligible subject types (product, wardrobe-detail, jewelry, prop, background-element). The closing clause 'Added to the library only when saveToLibrary is true' draws the boundary against the sibling save_reference_to_library.

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 invocation (isolating a single item from an existing photo) and warns that the call spends credits. It stops short of naming alternatives such as edit_image or estimate_cost, and never states when this tool is the wrong choice.

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

All Tasvr 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?