Skip to main content
Glama

MDEngine

by com.forcefieldsilicon
OverviewDiscussionsAdmin

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 offered classes and how jobs are priced. 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)
end_markerNoOptional line your deck prints when it truly finished (e.g. a `print DONE` at the end); a done job whose log lacks a line starting with it gets verdict=warnings, end_marker_missing=true
estimate_sNoYour runtime guess in seconds; informational only; the pre-check uses wall_limit_s net of credit held by your unfinished jobs
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.

  1. Changed2 schema fields changed
    • addedInput schema / properties / end_marker
      Added value: +{
+  "description": "Optional line your deck prints when it truly finished (e.g. a `print DONE` at the end); a done job whose log lacks a line starting with it gets verdict=warnings, end_marker_missing=true",
+  "type": "string"
+}
    • changedInput schema / properties / estimate_s / description
      Previous value: -"Your runtime guess in seconds; only used for the balance pre-check (min 900 s at the rate)"New value: +"Your runtime guess in seconds; informational only; the pre-check uses wall_limit_s net of credit held by your unfinished jobs"
  2. Changed1 schema field changed
    • changedInput schema / properties / gpu / description
      Previous value: -"GPU class; call account for the currently offered classes and hourly rates. Default any = cheapest available"New value: +"GPU class; call account for the offered classes and how jobs are priced. Default any = cheapest available"
  3. 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)"
  4. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare the mutation profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false) plus openWorld, so the bar is lower, yet the description adds real context: it reserves rather than launches, what the upload artifact must be (.tar.gz, <=2 GB, relative paths), and the exact follow-up call. It does not cover auth requirements or what happens to abandoned reserved jobs.

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?

Two sentences, zero filler. The role in the workflow is front-loaded, followed immediately by the concrete upload contract and the required next step.

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?

With no output schema, the description carries the return value (presigned upload_url) and the full lifecycle an agent needs: validate, reserve, upload, then call start_job. For an 8-parameter creation tool, nothing essential to invoking it correctly is missing.

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 100%, so the baseline is 3 and the schema already documents all eight parameters. The description still adds meaning by clarifying that the deck's input script is referenced with relative paths and lives at `input` inside the uploaded archive, which disambiguates the required parameter in the context of the upload step.

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?

Names a specific verb+resource (create_job / reserves a job id) and states its exact position in the pipeline: step 1 of a two-step path. It is clearly distinguishable from start_job and submit_job because it says this one only validates and reserves the id, returning an upload_url rather than launching work.

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?

Explicitly ties itself to 'big decks' and tells the agent the next call (start_job), which is strong sequencing guidance. The qualifier 'for big decks' implies the small-deck alternative (submit_job) without naming it, so the exclusion is only suggested rather than stated.

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
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources