s2docs MCP Server

Overview Schema Source Related Servers Discussions Admin

build_model

Writes a Source 2 .vmdl document for a mesh already in the addon, matching the shape the game compiler accepts. Returns the written path; set overwrite to replace an existing file.

Instructions

Write a Source 2 model document (.vmdl) for a mesh that is already inside the addon.

    `mesh` is addon-relative (e.g. models/probe/probe.dmx). The document copies the shape the
    game's own compiler accepts — compile it on a host with resourcecompiler afterwards
    (build_start). Returns the written path. Use overwrite=true to replace an existing .vmdl.

Input Schema

Name	Required	Description	Default
`game`	No	Game id: one of cs2, deadlock	cs2
`mesh`	Yes
`name`	Yes
`addon`	Yes	Addon name: lowercase [a-z0-9_], e.g. 'jump_arena'
`overwrite`	No
`translate`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false; the description adds the useful operational detail that overwrite=true will replace an existing .vmdl and that the tool returns the written path. It also discloses the important constraint that the document is only compiler-acceptable and must be built on a host with resourcecompiler, which an agent could not infer from annotations alone.

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 short sentences, front-loaded with the core action, then the path convention, then the follow-up build step. Slight redundancy with the multi-line indentation, but no wasted content.

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?

Covers what the tool produces, the path semantics, the overwrite behavior, and the downstream build step, and an output schema exists so return values need not be spelled out. The remaining gap is the unexplained `name` and `translate` parameters for a six-parameter write tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 33%, and the description compensates partially: it defines `mesh` as addon-relative with an example and explains `overwrite`. However, `name` and especially `translate` (an array of numbers, presumably an offset) are left entirely undefined in both schema and description.

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 artifact: writes a Source 2 model document (.vmdl) for a mesh already in the addon. It also distinguishes itself from the sibling build_start by clarifying that this tool only emits the document and that compilation happens elsewhere.

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 the sequencing rule (compile afterwards via build_start) and the condition for the overwrite flag (replace an existing .vmdl). It does not name an explicit alternative for building without writing a document, but the routing to build_start is clear enough.

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

Deploy Server