Skip to main content
Glama
ThatHunky

blockwright

by ThatHunky
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Build from ASCII layers

build

Place Minecraft structures from character-layer schematics, mapping palette characters to block states with rotation and dry-run preview before applying changes.

Instructions

Place a structure described as layers of characters. palette maps one character to a block state; rows run north→south (z), characters west→east (x); y is height above origin. Space leaves the world alone. Extra single blocks go in "blocks". Rotation keeps the min corner at origin. Run with dry_run=true first, and preview before that.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
labelNoShort label stored with the snapshot, e.g. "cottage walls"
worldNooverworld (default), nether, end, a minecraft:<dimension> id, or a Bukkit world folder name
blocksNoExtra single blocks at positions relative to origin, e.g. {"pos":[2,3,1],"block":"lantern[hanging=true]"}
layersNo
mirrorNox flips east↔west, z flips north↔south. Applied before rotation.none
originYesWorld position that the spec's (0,0,0) maps to: the min corner of the build
dry_runNoCompile and report without changing the world
paletteNoSingle character → block state, e.g. {"#":"stone_bricks","g":"glass_pane","." : "air"}. Space always means "leave the world alone".
rotationNoClockwise quarter turns seen from above. The min corner stays at origin.
snapshotNoSnapshot the affected box first so undo can revert it (needs world read access)
allow_unknown_blocksNoSkip block-name validation (for blocks newer than the bundled registry)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and it does disclose non-obvious behavior: rows map north→south, characters west→east, spaces are no-ops, and rotation keeps the min corner at origin. It also signals a write operation by directing dry_run=true. It stops short of explaining snapshot/undo behavior, but that is present in 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 dense sentences pack the purpose, coordinate axes, space sentinel, extra blocks, rotation invariant, and a safety workflow with no filler. It is front-loaded and every clause earns its place.

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 an 11-parameter, nested-object tool, the description provides the key mental model and the critical safety sequence, leaving details to a rich schema. It does not describe return values, but there is no output schema and the combination of description plus schema is sufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is very high (91%), and the schema already documents palette, layers, blocks, rotation, and snapshot. The description mostly restates the schema's semantics (orientation, space, rotation corner) rather than adding new parameter meaning; the baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific action—'Place a structure described as layers of characters'—and immediately supplies the coordinate semantics, so the agent knows the tool's domain. It is distinguishable from siblings like fill or paste_schematic by the ASCII-layer mechanism, though it never names an alternative explicitly.

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 provides an explicit safe workflow: 'Run with dry_run=true first, and preview before that.' This tells the agent to invoke preview before build and to use dry-run before actually placing. It does not contrast build with fill/place_shape/paste_schematic, but the context is clear.

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

Deploy Server

Other Tools