Skip to main content
Glama
Sign In
splatcraft

splatcraft

Official
by sandraschi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Local

Splat Train Local

splat_train_local

Train a 3D Gaussian Splat locally from a video or image directory using Nerfstudio or Postshot, then export the trained splat.ply to a target directory.

Instructions

Trains a 3D Gaussian Splat locally on RTX 4090 using Nerfstudio or Postshot.

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": {
      "input_path": "<input_path>",
      "output_dir": "<output_dir>"
    },
    "name": "splat_train_local"
  }
}

Input Schema

NameRequiredDescriptionDefault
engineNo"nerfstudio" or "postshot".nerfstudio
dry_runNoPlan execution commands without running heavy GPU steps.
input_pathYesPath to video or directory of images.
iterationsNoNumber of training iterations.
output_dirYesTarget export directory for trained splat.ply.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden; it does usefully add the hardware requirement (RTX 4090) and the local-execution constraint. However, it says nothing about training being long-running/blocking, GPU contention, cancellation, or what happens if output_dir already contains a splat — critical for a heavy compute job.

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?

A single front-loaded sentence with no wasted clauses; the verb, resource, hardware constraint, and engine options all appear immediately.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The output schema exists, so return values (splat.ply export) need not be explained, and the schema fully documents parameters. Still, for a long-running GPU training operation, the description omits runtime expectations, failure modes, and the sibling probe step, leaving meaningful gaps.

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 100%, so all five parameters including engine options, iterations, and dry_run are already documented in the schema. The description repeats the engine names but adds no format, constraint, or defaulting semantics beyond that, so the baseline of 3 applies.

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 gives a specific verb and resource ("Trains a 3D Gaussian Splat") plus a scoping constraint ("locally on RTX 4090") and the two supported engines. That distinguishes it from splat_convert and splat_create_world, though it never names the closest sibling, splat_probe_local_engines, which checks engine availability.

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

Usage Guidelines2/5

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

There is no explicit when-to-use guidance: nothing says to run splat_probe_local_engines first, nothing rules out remote/limited-hardware scenarios, and no prerequisites for input data are stated. The word "locally" hints at the context but leaves the agent to infer it.

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