Skip to main content
Glama

Read the blocks in an area

read_blocks
Read-onlyIdempotent

Returns full block states, block entity IDs, and counts for a box in saved Minecraft chunks, so agents can inspect and validate builds without changing the world.

Instructions

Returns the blocks in a box with their full states, block entity ids and a count per block. The server saves the world first and the tool reads the saved chunks, so it changes nothing. Limited to maxReadBlocks per call (32768 by default, for example 32x32x32); read big builds in parts. format "layers" (default) is compact, one line per row; "list" gives every non-air block as [x, y, z, state].

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": {
      "from": "<from>",
      "to": "<to>"
    },
    "name": "read_blocks"
  }
}

Input Schema

NameRequiredDescriptionDefault
toYesThe opposite corner [x, y, z], inclusive
fromYesOne corner [x, y, z]
formatNolayers
dimensionNoDimension. Default overworld.overworld

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly and idempotent, but the description adds real context: the server saves the world first and the tool reads saved chunks, so it changes nothing. It also discloses a concrete size ceiling (32768 blocks, e.g. 32x32x32), which annotations do not cover. Missing only output-shape details, which no output schema exists to supply.

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?

Three dense sentences, front-loaded with the return value, then the read-only behavior, then the size limit and format options. Nothing is wasted, though the final sentence is somewhat cramped and could be split for readability.

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?

With no output schema, the description does the job of explaining what is returned and in what shape. The size limit, read-only behavior, and format modes are all covered; only pagination/error behavior is unstated, which is minor for a read-only bulk tool.

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 75%, and the description compensates usefully: it explains what each 'format' value produces ('layers' is compact, one line per row; 'list' emits [x, y, z, state] per non-air block) and ties maxReadBlocks to the from/to box. Dimension is left to the schema, which already documents it.

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 ('Returns the blocks in a box') plus what comes back: full states, block entity ids, and a count per block. That level of detail clearly separates it from siblings like read_entities and clear_blocks.

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 for large reads ('Limited to maxReadBlocks per call... read big builds in parts'), which tells the agent how to behave. It does not explicitly name an alternative tool or state when not to use this one, so it stops short of full routing guidance.

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