Skip to main content
Glama

run_prepare

DestructiveIdempotent

Freezes a Slurm execution intent, inputs, environment, and rules, returning a revision for the next mutation so changed validation or stage cannot silently reuse an old run binding.

Instructions

Freeze a Slurm execution intent, input, environment and rules. Returns revision for the next mutation. Exact repetition reuses the same run; changed validation_id/stage never silently returns an old binding. To replace a confirmed unsubmitted prepared/cancelled/staging_failed run, use a new intent and supersedes=old run_id, retaining the sample_id. Submitted/unknown runs must be reconciled first. Native entry is a project-relative shell script; read lammps_reference before generation. Literal -in/-i inputs are reviewed before dispatch.

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": {
      "task_id": "<task_id>",
      "revision": "<revision>",
      "snapshot_id": "<snapshot_id>",
      "entry": "<entry>",
      "intent": "<intent>",
      "condition_id": "<condition_id>",
      "sample_id": "<sample_id>",
      "op_id": "<op_id>"
    },
    "name": "run_prepare"
  }
}

Input Schema

NameRequiredDescriptionDefault
entryYes
op_idYes
stageNoproduction
tokenNo
intentYes
purposeNoresearch
task_idYes
revisionYes
parent_idNo
sample_idYes
supersedesNo
snapshot_idYes
condition_idYes
validation_idNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare destructive=true and idempotent=true, but the description adds real semantics beyond them: exact repetition reuses the same run, while changed validation_id/stage never silently returns an old binding, and submitted/unknown runs must be reconciled first. It stops short of saying what exactly is invalidated when a binding is superseded, but the lifecycle behavior is unusually well disclosed.

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?

Five dense sentences, each carrying distinct information, with the core action and return value front-loaded before the lifecycle rules. Some phrasing is jargon-heavy ('Freeze a Slurm execution intent'), but nothing reads as filler.

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?

An output schema exists, so return values need not be explained, and the destructive/idempotent profile is covered by annotations plus the reuse and supersede rules. However, for a 14-parameter mutation tool, half the parameters remain undefined anywhere, which an agent would need in order to call it correctly.

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 0% across 14 parameters, so the description must carry the load, and it only partially does: it explains validation_id, stage, supersedes, sample_id retention, intent, and entry as a project-relative shell script. Parameters such as op_id, token, purpose, task_id, snapshot_id, condition_id, and parent_id get no meaning at all, leaving a substantial gap.

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 verb phrase 'Freeze a Slurm execution intent, input, environment and rules' names a specific operation and resource, and 'Returns revision for the next mutation' makes clear this is the preparation/binding step rather than dispatch. It is distinguishable from siblings like run_submit or check_run, though it never explicitly contrasts with batch_prepare, leaving some ambiguity about which prepare variant applies.

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 concrete when-to-use conditions: use a new intent plus supersedes=old run_id to replace a confirmed unsubmitted prepared/cancelled/staging_failed run, and reconcile submitted/unknown runs first. It also states a prerequisite ('read lammps_reference before generation') and a review gate for literal -in/-i inputs. No explicit negative case is given for other prepare-style siblings, which keeps it off a 5.

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