Ferret

Add or change a category

save_category

Adds a category, optionally inside another one (parentId) — "Power tools" under "Tools" — or, with id, renames one or moves it under another parent (null: top level).

Instructions

Adds a category, optionally inside another one (parentId) — "Power tools" under "Tools" — or, with id, renames one or moves it under another parent (null: top level). To add: name; check list_categories first so you don't add one twice, then use its id as categoryId on create_item, update_item or bulk_update_items. Returns the category with its id.

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": "save_category"
  }
}

Input Schema

Name	Required	Description
`id`	No	The category to change, from list_categories; leave out to add a new one
`name`	No	The category's name: "Power tools", "Kitchen appliances"
`parentId`	No	The category it's inside, from list_categories; null or left out: top level

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2026.11.10Nov 9, 2026

TDQS

A4.4/5.0

Behavior3/5

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

Annotations already declare this is a non-destructive, closed-world write, and the description usefully adds the upsert rule (id present = change, absent = add), the null-means-top-level semantics, and the return payload. It does not cover whether renaming affects child categories or items already assigned, or what happens on duplicate names, which matters for a mutation 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?

Front-loaded with the two modes, and every clause (nesting, null parent, dedupe check, downstream categoryId use, return value) carries information. The dash-heavy single sentence is dense and slightly harder to parse than a short bulleted split would be.

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?

All three optional parameters are accounted for, there is no output schema yet the description states it returns the category with its id, and the guidance closes the loop into the item-writing tools. Nothing an agent needs to invoke it correctly is missing.

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?

Schema coverage is 100% and the schema already defines id, name and parentId including null behavior, so the baseline is 3. The description still earns a bump by tying id to the rename/move outcome and demonstrating the parent-child relationship with a concrete hierarchy example.

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 specific verbs and resource: adds a category, optionally nested, or renames/moves one when id is supplied. The add versus upsert distinction is spelled out with a concrete example ("Power tools" under "Tools"), so an agent can tell it apart from list_categories and the other save_* siblings.

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 instructs checking list_categories first to avoid duplicates and then reusing the returned id as categoryId on create_item, update_item or bulk_update_items. That is a concrete when-to-use plus the follow-on call, not just implied usage.

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