Ferret

Remove something

remove

Destructive

Removes one thing from the household's records, by kind and id. Confirm with the person first. What each kind does: - item: only when it was added by mistake or should be gone from the records — for something sold, given away, thrown out…

Instructions

Removes one thing from the household's records, by kind and id. Confirm with the person first. What each kind does:

item: only when it was added by mistake or should be gone from the records — for something sold, given away, thrown out, lost or stolen use update_item with disposition, which keeps it for insurance. It stays in Recently deleted for 30 days (restore_item brings it back), then goes for good with its photos and documents.
warranty: one added by mistake or twice (an ended warranty stays on record as expired); its claims go with it. claim: a warranty claim filed by mistake.
maintenance: a task no longer needed — not one just done (that's complete_maintenance); its past times done stay in the item's history.
property / location: only when empty (no things anywhere in it, empty rooms inside go with it); otherwise refused — move the things first with bulk_update_items.
category: its things and subcategories move up to its parent. provider: their past visits stay, without the name. collection: its owned things stay (out of the collection); its want-list entries go. coverage_limit: a limit that no longer applies. Only remove (item) can be undone. Returns what was removed.

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": {
      "kind": "<kind>",
      "id": "<id>"
    },
    "name": "remove"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	Its id, from the tool that lists that kind (search_inventory, get_item, list_maintenance, list_locations…)
`kind`	Yes	What it is

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2026.11.10Nov 9, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already flag destructiveHint=true, but the description adds what the annotations cannot: a 30-day Recently deleted window with restore_item for undo (true only for item), permanent deletion including photos and documents, refusal on non-empty property/location, category children reparenting to parent, and provider visits surviving without the name. This is exactly the cascade and irreversibility detail an agent needs before calling 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?

Front-loaded with the core action, the confirmation requirement, and then a per-kind bullet structure that is easy to scan. Every bullet carries decision-relevant information; the text is dense but not padded, though a few fragments (e.g. 'claim: a warranty claim filed by mistake.') verge on terse to the point of ambiguity.

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?

For a 2-parameter, 10-way destructive dispatcher with no output schema, the description covers preconditions (empty containers), cascades, reversibility per kind, and what gets returned. Little an agent would need to know before invoking 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%, so the baseline is 3, but the description goes beyond the schema's bare enum ('What it is') by explaining the semantic and side effects of each kind value — e.g. warranty deleting its claims, collection keeping owned things but dropping want-list entries. The 'id' parameter only gets the pointer already present in the schema, so it is not a full 5.

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?

Opens with a specific verb and resource ('Removes one thing from the household's records, by kind and id') and immediately scopes it relative to siblings (update_item with disposition, restore_item, complete_maintenance). An agent can tell this apart from the many save_*/update_* tools 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?

Explicitly routes each case: sold/given away/thrown out/lost/stolen goes to update_item with disposition, completed maintenance goes to complete_maintenance, and non-empty property/location must be emptied via bulk_update_items first. It also states the precondition 'Confirm with the person first', which is unusually actionable guidance for a destructive tool.

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