Skip to main content
Glama

write_hint_brush

Creates a hint brush that marks a slab’s cutting plane with TOOLS/TOOLSHINT and other faces with TOOLS/TOOLSSKIP to shape a map’s visibility tree in source VMF.

Instructions

Creates a hint brush: a slab carrying TOOLS/TOOLSHINT on the plane vvis should cut along and TOOLS/TOOLSSKIP everywhere else. This is the one lever that shapes a map's visibility tree directly, and nothing in a compiled .bsp records it -- vvis consumes hints and they are gone from the file, so this can only be done on the source. rotateZ makes the cut diagonal, which is what a mapper does when a city's streets do not run along the axes. Verify by compiling before and after and comparing read_visleaf_stats: a hint that moves no leaf count did nothing.

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>",
      "mins": "<mins>",
      "maxs": "<maxs>"
    },
    "name": "write_hint_brush"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxsYesUpper corner of the slab, before any rotation.
minsYesLower corner of the slab, before any rotation.
pathYesPath to the .vmf, absolute or relative to the repo root.
backupNoCopy the file to <file>.bak before writing. Nothing is copied on a no-op.
dryRunNoCheck and report without writing. Every verification runs either way.
confirmNoRequired (true) to run this tool: it writes or executes.
rotateZNoDegrees to turn the slab about its own centre. 45 gives a diagonal cut. Corners are rounded to whole units, so the faces stay exactly planar.
hintFacesNoWhich faces carry the hint. 'largest' (default) hints the two biggest opposing faces, which for a thin slab is the plane you meant. 'all' hints every face.

Output Schema

NameRequiredDescriptionDefault
gridYes
maxsYes
minsYes
pathYes
validYes
volumeYes
solidIdYes
writtenYes
nextStepYes
warningsYes
backupPathYes
hintFaceCountYes
skipFaceCountYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

A4.3/5.0
Behavior4/5

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

Annotations carry only a title, so the description bears the behavioral load, and it does disclose the key non-obvious trait: hint brushes vanish from the compiled .bsp, so the effect is source-only and invisible in the output file. It also explains the no-op case implicitly ("a hint that moves no leaf count did nothing"). It could say more about failure modes or in-place editing of an existing brush, but the domain behavior is well covered.

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?

Four sentences, front-loaded with the definition, and the closing verification sentence is actionable rather than filler. Slightly dense in the first sentence, but no sentence 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?

With an output schema present, return values need no explanation, and the description covers the write target, the source-only constraint, the rotation semantics, and how to validate the result. Remaining gaps — what happens if a hint brush already exists at that location, or error conditions — are minor for a mutation tool whose parameters are fully documented.

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 3 is the baseline; the description earns above that by tying rotateZ to a concrete mapper scenario (diagonal cuts for cities whose streets are not axis-aligned), which gives the parameter intent rather than just syntax. It leaves hintFaces, confirm, and dryRun entirely to the schema, which is acceptable given full coverage.

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 ("Creates a hint brush") and immediately defines what that resource is: a slab carrying TOOLS/TOOLSHINT on the cut plane and TOOLS/TOOLSSKIP elsewhere. That level of specificity lets an agent distinguish it from generic brush writers like write_vmf_solid without opening a schema.

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 a clear usage constraint — this can only be done on source .vmf files because vvis consumes the hint data — and names a concrete verification path via compiling and read_visleaf_stats. It does not, however, explicitly route an agent away from sibling brush tools when a plain solid is wanted, so it stops short of full when/when-not guidance.

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