Skip to main content
Glama

measure_vmf_clearance

Measures actual free width and headroom at a point in a .vmf using a swept player hull, finding the narrowest direction and naming the brush that limits each clearance.

Instructions

How much room there actually is at a point in a .vmf: the free width across, the headroom, and what stops each measurement. Measured with a swept player hull rather than a ray, because that is the question -- a line passes a 24-unit gap that nobody fits through, and reports it as clear. The narrowest direction is found rather than assumed, since a corridor is wide one way and long the other, and a diagonal alley is narrow diagonally. Every number names the brush that bounded it.

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": {
      "path": "<path>",
      "at": "<at>"
    },
    "name": "measure_vmf_clearance"
  }
}

Input Schema

NameRequiredDescriptionDefault
atYesWhere to measure, in Hammer units.
axisNoMeasure across this direction only. Omit to search for the narrowest.
hullNoSource's own player hulls: 32x32x72 standing, 32x32x36 crouching.standing
maskNo`player` counts clip brushes, which are invisible and stop people.player
pathYes

Output Schema

NameRequiredDescriptionDefault
atYes
hullYes
pathYes
notesYes
floorZYes
hullFitsYes
boundedByYes
standingAtYes
widthUnitsYes
insideSolidYes
widthMetresYes
headroomUnitsYes
narrowestAxisYes
ceilingBrushIdYes
headroomMetresYes
headroomUnboundedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

A3.8/5.0
Behavior4/5

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

With no annotations beyond a title, the description carries the full burden and does disclose genuine method: it explains that measurement uses a swept player hull, that the narrowest direction is searched rather than assumed, and that every result is attributed to a bounding brush. Still missing are the operational facts an agent needs — that it is a pure read, cost on large maps, and behavior when 'at' is embedded inside a solid.

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 sentences, front-loaded with the answer (what is measured) and followed by two justifications that each carry information an agent could act on. The em-dash asides are slightly chatty but nothing is redundant.

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?

An output schema exists, so return-value details are correctly omitted, and the description covers the remaining burden: methodology, direction search, and per-number attribution. The gaps are edge-case behavior (point inside geometry, unbounded/open sky directions) that a measurement tool of this complexity would benefit from stating.

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 already 80%, yet the prose adds real meaning on top: the hull rationale explains why standing/crouching matters, the 'corridor is wide one way and long the other' line justifies omitting axis for a narrowest-direction search, and 'clip brushes, which are invisible and stop people' motivates the mask choice. The 'path' parameter and 'at' units get no prose treatment beyond the schema.

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 concrete verb+resource: measure the actual free width, headroom and blockers 'at a point in a .vmf'. That is enough to separate it from build/edit siblings like edit_vmf or write_vmf_solid. It never names the closest analogue (measure_vmf_approach) or the ray-based read_vmf_trace, so explicit sibling differentiation is left to inference.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the 'swept hull rather than a ray' rationale tells an agent to pick this when the question is whether a player physically fits, which implicitly excludes the ray-trace tool. There is no explicit when-to-use sentence, no exclusions, and no mention of alternatives such as measure_vmf_approach for pathing questions.

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