Skip to main content
Glama

Remove entities

remove_entity
Destructive

Remove Minecraft entities without drops by UUID or type, optionally within a radius; use dryRun to preview counts before deleting.

Instructions

Remove entities without drops: one by uuid, or many by types, such as dropped items, arrows, or a mob farm's overflow, optionally within a radius of x, y, z. Many at once never touches players, skips named mobs and tamed pets unless includeNamed is true, takes the nearest first up to max, and dryRun only counts. Try dryRun first and tell the user what would go.

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_entity"
  }
}

Input Schema

NameRequiredDescriptionDefault
xNoCenter X
yNoCenter Y
zNoCenter Z
maxNoRemove at most this many; the server caps it (1000 by default)
uuidNoOne entity
typesNoEntity keys, such as ["minecraft:item", "minecraft:arrow"]
worldNoWorld name, such as `world`, `world_nether`, `world_the_end`, or a key like `minecraft:the_nether`world
dryRunNoOnly count what would be removed
radiusNoBlocks around x, y, z
includeNamedNoAlso remove named mobs and tamed pets

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv4.2.1
    • addedInput schema / properties / x / description
      Added value: +"Center X"
    • addedInput schema / properties / y / description
      Added value: +"Center Y"
    • addedInput schema / properties / z / description
      Added value: +"Center Z"
  2. First observedv4.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations declare destructiveHint=true and idempotentHint=false; the description goes well beyond that by disclosing that players are never touched, that named mobs and tamed pets are skipped unless includeNamed is true, that bulk removal takes the nearest first up to max, and that dryRun only counts. These are non-obvious safety behaviors the agent could not infer from the schema.

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 sentences, each dense with unique information: mode selection, then exclusions/ordering, then the dryRun recommendation. The pre-flight advice lands last where an agent will act on it, and nothing is repeated from the schema.

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 10-parameter destructive tool with no output schema, the description covers modes, exclusions, ordering, and the dry-run workflow. It leaves one real gap: no statement of what happens if neither uuid nor types is supplied, nor what a dryRun call returns (a count? identifiers?) — though 'only counts' hints at it.

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; the description earns above that by explaining how parameters interact — uuid vs types select different modes, includeNamed gates an otherwise invisible exclusion, radius is anchored at x/y/z, and max is applied nearest-first. It doesn't restate the server-side cap meaningfully (that is in the schema), so it is not a 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?

States a specific verb and resource ('Remove entities') and immediately splits the two operating modes: single by uuid, bulk by types. 'Without drops' is a concrete disambiguator that distinguishes it from a generic kill command, and the phrasing lets an agent tell it apart from list_entities, spawn_entity, and update_entity 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 Guidelines4/5

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

Gives actionable guidance: 'Try dryRun first and tell the user what would go,' which is exactly the precondition an agent needs before a destructive bulk operation. It does not name an alternative tool (e.g. run_command with a kill selector) or state when bulk-by-types is inappropriate, so it stops short of full when/when-not coverage.

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