Skip to main content
Glama

render_vmf_view

Render a .vmf from a chosen camera and return an image, so you can inspect map geometry, room size, and occlusion instead of inferring them from coordinates.

Instructions

Renders a .vmf from a camera and returns the picture, so the shape of a place can be LOOKED at rather than inferred from coordinates. Flat colour per face, one light, no textures and no props: it shows form and occlusion -- what stands where, what hides what, how much room there is at eye height -- and it deliberately does not show atmosphere, which only a capture from the running game can. Camera convention is Source's own (x forward, y left, z up; angles pitch/yaw/roll; fov horizontal), the same one gmod-mcp's read_view reports, so a rendering and an in-game capture from the same numbers frame the same thing. A face's colour is a stable hash of its material, so the same wall is the same colour in two renderings an edit apart.

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>"
    },
    "name": "render_vmf_view"
  }
}

Input Schema

NameRequiredDescriptionDefault
fovNoHorizontal field of view.
nearNo
pathYesPath to the .vmf, absolute or relative to the repo root.
standNoPut the eye where a standing player's would be: drop to the floor under `origin` and rise to eye height. Use this rather than guessing a z.
widthNo
anglesNoPitch, yaw, roll in degrees. Positive pitch looks down, as Source means it.
heightNo
lookAtNoAim at this point instead of giving angles. Overrides `angles`.
originNoEye position. Omit with `fromEntity`, or with neither to frame the whole map.
eyeHeightNoAdded to the origin's z. 64 is Source's standing eye height.
fromEntityNoStand at this targetname's origin -- an info_player_start, say.
lookAtEntityNoAim at this targetname's origin. Overrides `angles` and `lookAt`.

Output Schema

NameRequiredDescriptionDefault
fovYes
pathYes
notesYes
widthYes
anglesYes
heightYes
originYes
pngBytesYes
brushCountYes
facesDrawnYes
facesBehindYes
facesCulledYes
insideSolidYesThe eye is inside a brush, so the picture is the inside of a wall.
skyFractionYes
voidFractionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.0.24-alpha

TDQS

A4/5.0
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 full load and does it well: flat colour per face, one light, no textures or props, what it shows (form, occlusion, room at eye height) and what it omits. It even discloses a stable material-to-colour hash, which is the key behavior for comparing renderings across an edit.

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?

Front-loaded with the verb and the payoff, then limitations, then the camera convention. It is a single dense paragraph and every sentence carries information; the colour-hash sentence is the most expendable but still earns its place for diffing renderings.

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 a 12-parameter rendering tool with an output schema, the description supplies the mental model an agent needs: what the image will and will not show, and the coordinate conventions governing the camera parameters. Resolution, near-plane and performance expectations are left to the schema defaults.

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 75%, so the baseline is 3, but the description adds real meaning on top: the Source camera convention (x forward, y left, z up; pitch/yaw/roll; horizontal fov) that makes origin, angles and lookAt interpretable. Some parameters (near, width/height, eyeHeight) get no narrative 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?

States a specific verb and resource: 'Renders a .vmf from a camera and returns the picture.' It also frames the intent (form and occlusion rather than atmosphere), which separates it in spirit from a game capture. It never names its closest siblings (render_vmf_plan, render_vmf_tour), so the agent must infer how those differ.

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?

'so the shape of a place can be LOOKED at rather than inferred from coordinates' gives the positive case, and 'deliberately does not show atmosphere, which only a capture from the running game can' gives an explicit exclusion with an alternative. What is missing is routing guidance to the sibling render tools when a plan or tour is wanted instead.

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