Skip to main content
Glama

set_landscape_height_in_box

DestructiveIdempotent

Raise or lower terrain by adding a Z delta to every heightmap vertex inside a world-space box. Use box_min/box_max or center/extent to define the region.

Instructions

Raise or lower terrain: add delta_z world units to every heightmap vertex inside a world-space box (give box_min/box_max, or center/extent). A RELATIVE edit -- to force a region to one absolute height use flatten_landscape_in_box, and to soften the seams afterwards use smooth_landscape_in_box. Check vertices_modified in the reply: a zero means the box missed the terrain, which is what a wrongly-signed world coordinate looks like.

Returns: { landscape_actor_name: string, delta_z: number, delta_steps: int, applied: bool, vertices_modified: int, region_width: int, region_height: int, region: [int] }

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
centerNoOptional [x, y, z] box center (alternative to box_min/box_max)
extentNoOptional [x, y, z] box half-extents (alternative to box_min/box_max)
box_maxNoOptional [x, y, z] world-space box maximum
box_minNoOptional [x, y, z] world-space box minimum
delta_zNoWorld Z delta to apply to every vertex in the region
landscape_actor_nameNoOptional landscape actor name, defaults to first found

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

A4.7/5.0
Behavior4/5

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

The description adds real context beyond the annotations: it declares the edit is RELATIVE (not absolute), names what is modified (heightmap vertices within the box), and discloses the key failure mode (vertices_modified == 0 means the box missed the terrain). However, it does not mention permission/auth or undo/persistence requirements, and its 'add delta_z to every vertex' semantics sit in tension with the idempotentHint=true annotation (repeated calls would accumulate), leaving the re-run behavior ambiguous.

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?

Front-loaded with the core action, then alternatives, then a verification tip, then the return shape. Dense but every sentence carries distinct, non-redundant information; no filler.

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?

With no output schema, the description supplies the full return shape (landscape_actor_name, delta_z, vertices_modified, region, etc.) and explains the most important field, vertices_modified. Combined with the sibling routing and coordinate alternatives, nothing an agent needs to call it correctly is missing.

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 adds meaning beyond the schema by clarifying the two alternate coordinate spellings ('give box_min/box_max, or center/extent') and by framing delta_z as a relative world-space offset, plus the wrongly-signed-coordinate pitfall, which the schema does not convey.

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+resource+effect: 'add delta_z world units to every heightmap vertex inside a world-space box.' It explicitly names the two sibling tools it is NOT (flatten_landscape_in_box for absolute heights, smooth_landscape_in_box for seams), so an agent can distinguish it without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Gives explicit when-to-use guidance and alternatives: 'to force a region to one absolute height use flatten_landscape_in_box, and to soften the seams afterwards use smooth_landscape_in_box.' It also tells the agent how to verify success (check vertices_modified) and what a zero implies, which is actionable usage context.

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