Ferret

Start or change a collection

save_collection

Instructions

Starts a collection — coins, records, trading cards, LEGO sets — optionally of one kind of thing (templateId, from list_templates) whose fields become its columns, or, with id, renames one or changes its description or kind. To add: name; check list_collections first so you don't start one twice. Then add things to it with create_item (collectionId; wanted: true for its want list) or update_item. Returns the collection 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_collection"
  }
}

Input Schema

Name	Required	Description
`id`	No	The collection to change, from list_collections; leave out to add a new one
`name`	No	The collection's name: "US quarters", "Vinyl records"
`templateId`	No	The kind of thing in it, from list_templates: its fields are the collection's columns
`description`	No	What it is, what's being looked for

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2026.11.10Nov 9, 2026

TDQS

A4.5/5.0

Behavior4/5

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

With readOnlyHint=false, destructiveHint=false, and openWorldHint=false already defined, the description adds real context: that this is an upsert whose mode depends on the presence of id, that template fields become columns, and that the collection with its id is returned. It does not say what happens to existing items or fields when 'kind' (templateId) is changed on an existing collection, which is the one consequential behavior left undisclosed.

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 create-vs-update distinction, then inputs, then follow-up paths; almost every clause carries information. The parenthetical stacking (templateId, from list_templates) and em-dash asides make it dense but not bloated.

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 4-parameter upsert with no output schema, the description supplies the workflow (pre-check, create, then populate) and the return value ('Returns the collection with its id'). The gap is the lack of any note on effects of changing a collection's kind or on duplicate-name behavior.

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 description coverage is 100%, so the baseline is 3, but the description adds relational meaning: id switches the call into a rename/description/kind change, name is the minimum for creation, and templateId should come from list_templates. That is more than a restatement of the schema, though it does not cover length limits or constraints.

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 verb and resource, captures both modes (create without id, update with id), and distinguishes the tool from siblings by linking to list_templates, list_collections, create_item, and update_item. An agent can tell exactly what this does 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 Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives an explicit pre-call check ('check list_collections first so you don't start one twice'), states the minimum input for creation ('To add: name'), and routes the agent onward to create_item or update_item, including the wanted: true variant. That is when-to-use and next-step guidance rather than implied usage.

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