Skip to main content
Glama

splat_generate

Generate Gaussian-splat worlds from local videos or image sets, then track background jobs and retrieve completed asset paths.

Instructions

Generate or inspect a Gaussian-splat world from local media.

Operations: from_video - start a job from a video file (video_path required) from_images - start a job from a set of images (image_paths required) status - check a job's status (job_id required) list - list all known jobs get_asset - return asset paths for a completed job (job_id required)

from_video/from_images return IMMEDIATELY with status="running" - the real ns-process-data -> ns-train -> ns-export pipeline runs as a background task (real training takes real minutes, not seconds). Poll with operation="status" until status is "done" or "failed".

Return Format

Always a dict with a success bool and a human-readable message. Success paths also carry the documented payload keys (job_id, status, jobs, asset_paths). Error paths carry success: False plus an error key with the machine-readable reason; the error key is kept for backward compatibility with existing clients.

Examples

splat_generate(operation="from_video", video_path="D:/cap/walk.mp4") -> {"success": True, "job_id": "...", "status": "queued", "message": ...} splat_generate(operation="status", job_id="<id>") -> {"success": True, "job_id": "<id>", "status": "running", "message": ...} splat_generate(operation="list") -> {"success": True, "jobs": [...], ...}

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": {
      "operation": "<operation>"
    },
    "name": "splat_generate"
  }
}

Input Schema

NameRequiredDescriptionDefault
job_idNo
operationYes
video_pathNo
image_pathsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations supplied, the description carries the full load and mostly succeeds: it discloses that from_video/from_images launch a real background pipeline (ns-process-data -> ns-train -> ns-export) that returns immediately with status='running', and that completion requires polling rather than a quick response. It does not mention permissions, disk/resource cost, or whether jobs can be cancelled or cleaned up.

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?

Structure is strong: operations list first, then the async caveat, then return format, then examples, so the reader is front-loaded with the decision-relevant content. The examples mildly duplicate the Return Format section, but each shows a distinct operation and none are pure filler.

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 tool with an output schema, an async job lifecycle, and four loosely-typed parameters, the description covers the async contract, the per-operation requirements, and the success/error envelope. Remaining gaps are operational rather than invocation-blocking (no auth, no cancellation semantics, no runtime expectations beyond 'real minutes').

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 description coverage is 0%, so the description must compensate, and it does the most important part by stating the conditional requirement of each parameter per operation ('video_path required', 'image_paths required', 'job_id required'). It adds no detail on accepted path formats, whether image_paths has cardinality limits, or where job_id values come from.

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 opening sentence names a specific verb pair and resource ('Generate or inspect a Gaussian-splat world from local media') and the operations block enumerates every mode with its required argument, so the tool's scope is unambiguous. It stops short of naming or differentiating itself from the sibling 'splat_engine_status', which the operation='status' mode could plausibly be confused with.

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?

Usage is spelled out per operation: which argument each mode requires (video_path, image_paths, job_id) and, critically, the instruction to poll with operation='status' until the job reaches 'done' or 'failed'. There is no explicit when-not guidance and no routing to sibling tools such as splat_engine_status, so it lands below the top band.

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