Skip to main content
Glama
Sign In

Marsell

by com.getmarsell
OverviewDiscussionsAdmin

Take something out of the setup

remove_from_setup
Destructive

Takes out what was added by mistake: products or rivals by name, pictures or logos by file id, fonts by role, social accounts by address, guides by id, and files by id (a file of this project you added and no longer use, such as an earlier logo or font you replaced; only while the setup is open, in a project this setup made). A file taken out leaves the project's files too (as Brand's remove does), and so does a logo or font a new one replaces; nothing the owner added is touched.

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": "remove_from_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
filesNoFile ids (get_setup's files) of this project you added and no longer use.
fontsNoFonts to take out, by role.
logosNoLogos to take out, by file id.
guidesNoGuides to take out, by id (get_setup).
rivalsNoRivals to take out, by name.
picturesNoPictures to take out, by file id.
productsNoProducts to take out, by name.
social_accountsNoSocial accounts to take out, by their address.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior5/5

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

Beyond the destructiveHint=true annotation, the description discloses the cascade: 'A file taken out leaves the project's files too (as Brand's remove does), and so does a logo or font a new one replaces.' It also states an ownership boundary ('nothing the owner added is touched') and a lifecycle precondition (setup must be open). These are exactly the side effects an agent needs before invoking a destructive tool.

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?

It is a single dense sentence with zero redundant framing and the entity list is front-loaded. The nested parenthetical about files is hard to parse on first read, which slightly hurts scanability for a long definition.

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 destructive, eight-parameter, all-optional tool with no output schema, the description covers side effects, scope and ownership. It does not say what happens when a supplied name or id does not match, nor what the call returns, which is the remaining gap.

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%, so each of the eight parameters is already documented with its identifier type. The description restates those keys ('by file id', 'by role', 'by address') and adds eligibility nuance for files, but contributes no new format or validation detail beyond the schema baseline.

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 description names a specific removal verb and enumerates every removable entity with its identifier key (products/rivals by name, pictures/logos by file id, fonts by role, social accounts by address, guides and files by id). This clearly separates it from the add_* siblings (add_products, add_logo, add_font) and from the other remove tools in the family.

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 states the governing condition precisely: undo something 'added by mistake', only for a file 'you added and no longer use' such as an earlier logo or font you replaced, and only 'while the setup is open, in a project this setup made'. It does not name an alternative tool for cases that fail those preconditions (e.g. removing a product outside setup), but the inclusion criteria are explicit.

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

All Marsell toolsInspect
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