Skip to main content
Glama

Map surface heights

get_height_map
Read-onlyIdempotent

Finds the highest non-air block Y for each column in an X/Z area, returning absolute ground heights (null for empty columns) to plan builds and survey terrain.

Instructions

Find the ground: for each column of an X/Z area, the Y of the highest block that is not air.

heights[z][x] is an absolute Y (null for an empty column): rows go north to south (+Z), entries west to east (+X). surface uses the same layout with characters from surface_palette. Build on a column at heights + 1. Scans (area x height) blocks, at most 100,000; narrow y_min/y_max for big areas.

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": {
      "x1": "<x1>",
      "z1": "<z1>",
      "x2": "<x2>",
      "z2": "<z2>"
    },
    "name": "get_height_map"
  }
}

Input Schema

NameRequiredDescriptionDefault
x1YesX of one corner of the box (inclusive).
x2YesX of the opposite corner (inclusive).
z1YesZ of one corner of the box (inclusive).
z2YesZ of the opposite corner (inclusive).
y_maxNoHighest Y to scan.
y_minNoLowest Y to scan; narrow the range around the expected ground.
ignore_blocksNoBlock ids to treat as empty, e.g. ['water', 'oak_leaves', 'short_grass'] to find solid ground under water or trees. Air is always empty.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: a scan-cost model (area x height, capped at 100,000 blocks) and null results for empty columns. It does not say what happens when the cap is exceeded (error vs. partial result), which is the main remaining behavioral gap.

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?

Dense but front-loaded: purpose first, then output layout, then the build-offset hint, then the cost constraint. Backticked identifiers and parenthetical axis directions keep it scannable with no filler sentences.

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?

Despite seven parameters, the definition covers what an agent needs: the query semantics, the returned array indexing, the block-selection caveat, and the performance ceiling. An output schema exists, so the extra return-layout detail is a bonus rather than a gap.

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 earns a step up by linking y_min/y_max to the scan-cost limit and by clarifying that ignore_blocks treats air as always empty — meaning that is not a field-level detail. It adds little on x1/z1/x2/z2 beyond the schema.

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 precise verb and resource — 'Find the ground: for each column of an X/Z area, the Y of the highest block that is not air' — which unambiguously distinguishes this 2D surface map from point/volume siblings like get_block or get_blocks without needing to name them.

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 real usage context: it explains that structures should be built on 'heights + 1' and that large areas should have y_min/y_max narrowed. It stops short of explicitly naming alternative tools or stating when this is the wrong choice over get_block/get_blocks, so no exclusions are offered.

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