Skip to main content
Glama

Place blocks

set_blocks
Destructive

Place single Minecraft blocks or fill a box between two corners, choosing replace, keep-air, or replace-type modes and optional physics updates.

Instructions

Place up to 64 single blocks (blocks), or fill a box between two corners, inclusive (box). A block is a key or full state: stone, minecraft:oak_stairs[facing=east]. Box modes: replace sets everything, keep only fills air, replace_type only changes blocks of type replace; the server caps the volume (32768 blocks by default). physics updates neighbors (sand falls, water flows). WorldAPI keeps what was there until the server stops, so undo_change can put it back; a box answers its change id. Still confirm big changes with the user, and read the box with get_block's area first.

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": "set_blocks"
  }
}

Input Schema

NameRequiredDescriptionDefault
boxNoFill between two corners, inclusive
worldNoWorld name, such as `world`, `world_nether`, `world_the_end`, or a key like `minecraft:the_nether`world
blocksNoSingle blocks at x, y, z
physicsNoSand falls, water flows

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv4.2.1
    • addedInput schema / properties / blocks / description
      Added value: +"Single blocks at x, y, z"
    • addedInput schema / properties / box / description
      Added value: +"Fill between two corners, inclusive"
    • addedInput schema / properties / physics / description
      Added value: +"Sand falls, water flows"
  2. First observedv4.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With annotations already declaring destructiveHint=true and idempotentHint=false, the description adds substantial non-obvious behavior: the 32768-block server volume cap, per-mode semantics (replace/keep/replace_type), that physics triggers neighbor updates like falling sand and flowing water, and that WorldAPI retains prior state until server stop so undo_change can restore it. That is well beyond what the annotation block conveys. It does not describe return shape beyond a box's change id or failure modes, so it falls short of a 5.

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?

Core capability, then mode semantics, then side effects, then recovery/safety — well ordered and front-loaded. It is dense as a single paragraph with parenthetical asides, so it is efficient but slightly harder to scan than a bulleted form.

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, nested-object, four-parameter mutation tool it covers volume limits, physics side effects, undoability, and the confirmation expectation, and it points to get_block for pre-reading. Missing only permission/error behavior, which the absence of an output schema leaves unaddressed.

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 still earns credit by giving concrete block-value syntax ("`stone`, `minecraft:oak_stairs[facing=east]`") and by explaining what each `mode` value does and that `replace` names the type targeted under replace_type. This meaningfully enriches enum and nested-object parameters the schema only constrains structurally.

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 opens with a specific verb and resource: "Place up to 64 single blocks (`blocks`), or fill a box between two corners, inclusive (`box`)." It immediately makes the two operating modes and their parameter names distinguishable, which no sibling tool shares.

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 gives explicit workflow guidance — "read the box with get_block's area first" and "confirm big changes with the user" — and names undo_change as the recovery path, which is useful routing context among the many siblings. It stops short of stating when to prefer run_command or /setblock instead, so it is clear context without full alternative coverage.

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