Skip to main content
Glama

MDEngine

by com.forcefieldsilicon

Create a job (returns upload URL)

create_job

Step 1 of the two-step path for big decks: validates the spec, reserves a job id, returns a presigned upload_url. PUT the deck as a .tar.gz (<= 2 GB, relative paths, input at input) to upload_url, then call start_job.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
gpuNoGPU class; call account for the currently offered classes and hourly rates. Default any = cheapest available
inputYesRelative path of the LAMMPS (or runner) input script inside the deck, e.g. in.lmp
labelNoFree text <= 120 chars shown in job lists
launchNoLaunch template; omit for the default KOKKOS/CUDA LAMMPS command line
runnerNoRunner flavour: lammps (default) or openmm (beta)
estimate_sNoYour runtime guess in seconds; only used for the balance pre-check (min 900 s at the rate)
wall_limit_sNoHard cap in seconds (default 14400, max 86400); the job fails at the cap and is billed to it

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / properties / gpu / description
      Previous value: -"GPU class: any (cheapest available, default), rtx4090, a100 -- see account.rate_table"New value: +"GPU class; call account for the currently offered classes and hourly rates. Default any = cheapest available"
    • changedInput schema / properties / runner / description
      Previous value: -"Runner flavour: lammps (default) or openmm"New value: +"Runner flavour: lammps (default) or openmm (beta)"
  2. First observed

TDQS

A4.5/5.0
Behavior4/5

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

The description discloses key behaviors: it validates the spec, reserves a job ID, and returns a presigned upload URL, without starting the job. It explains that the caller must upload and then call start_job, making the workflow transparent. It does not contradict the annotations (readOnlyHint false, destructiveHint false, idempotentHint false).

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?

The description is extremely concise, using two clear sentences. It front-loads the primary purpose and provides step-by-step guidance without any filler or redundancy, making it easy to parse quickly.

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

Completeness5/5

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

Having no output schema, the description adequately explains what the tool returns (a presigned upload URL and a reserved job ID) and precisely what to do with that output (PUT the deck, then call start_job). It provides enough context for the caller to complete the workflow successfully.

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?

All seven parameters are fully described in the schema with 100% coverage, so the baseline is 3. The tool description adds extra semantic context not in the schema by specifying that the deck must be a .tar.gz, ≤2GB, with relative paths and the input at `input`, enriching parameter understanding.

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?

The description clearly states the tool's role as the first step in a two-step process, explicitly naming the actions (validate, reserve, return presigned URL) and the follow-up call to start_job. It distinguishes itself from siblings by referencing the two-step path and 'big decks', making its specific use case unambiguous.

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?

The description gives direct usage instructions: PUT the deck to the returned URL and then call start_job. It mentions 'big decks' and 'two-step path', implying a contrast with a one-step alternative (e.g., submit_job), though it does not explicitly name when to prefer this tool over other siblings.

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

All MDEngine toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4.3/5.0
Disambiguation5/5

Each tool serves a distinct purpose: account and capabilities cover account/configuration info, while create_job, start_job, and submit_job represent clearly differentiated job submission stages. Monitoring, results, cancellation, and deletion tools are all non-overlapping.

Naming Consistency4/5

Tool names mostly follow a clear snake_case verb_noun pattern (cancel_job, create_job, delete_results, list_jobs, start_job, submit_job). A few noun-only names like account, capabilities, job_status, and job_results deviate slightly, but the pattern remains recognizable and predictable.

Tool Count5/5

With 12 tools, the set covers the full job lifecycle without being bloated. Each tool maps to a meaningful operation, and the count is well within the typical 3-15 range for a domain-specific server.

Completeness5/5

The tool surface covers the necessary workflow: checking account/capabilities, submitting and starting jobs, monitoring status/logs, retrieving results, canceling jobs, and deleting results. No essential operation for the stated GPU job management domain appears missing.

Resources