Skip to main content
Glama

Create a sandbox

argon_sandbox_create

Create an isolated, disposable MongoDB sandbox from a project branch and get a connection string. Use any MongoDB driver, capture writes as versioned history, then merge, undo, or let TTL reclaim it.

Instructions

Fork an isolated, disposable copy of a MongoDB branch and get a connection string. Work against it with any MongoDB driver; every write is captured as versioned history. Merge the result back, undo it, or let the TTL reclaim it.

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": {
      "project": "<project>"
    },
    "name": "argon_sandbox_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
fromNoParent branch to fork (default: main)
nameNoSandbox name (default: generated)
actorNoLabel for all native writes on this branch/run; not individual writer identity
projectYesProject name
credentialNoIssue a MongoDB credential with read/write access only to this sandbox (default: false)
ttl_minutesNoMinutes until the sandbox is reclaimed (default: 60)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.12.0
    • addedInput schema / properties / credential
      Added value: +{
      +  "description": "Issue a MongoDB credential with read/write access only to this sandbox (default: false)",
      +  "type": "boolean"
      +}
  2. First observedv2.8.1

TDQS

A4/5.0
Behavior4/5

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

The annotations already state readOnly=false and destructive=false, but the description adds genuinely new behavior: the object is disposable, every write is captured as versioned history, and TTL reclamation happens automatically after ttl_minutes. It doesn't clarify whether repeated forks with the same name collide or how merge outcomes are surfaced, which keeps it from a 5.

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?

Three short sentences: the core action and result first, then how to use it, then the exit paths. No filler and nothing buried.

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?

With no output schema, the description correctly states the return value (a connection string) and covers the full lifecycle including reclamation. What is missing is what happens on merge failure or conflict, but for a create tool this is close to complete.

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 every parameter including from, name, actor, credential, and ttl_minutes is already documented in the schema. The description only implicitly connects to credential via 'get a connection string,' adding no syntax or default detail beyond what's structured.

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 leads with a specific verb and resource: 'Fork an isolated, disposable copy of a MongoDB branch and get a connection string.' That framing ('fork,' 'disposable copy,' 'connection string') separates it from the creation siblings like snapshot or pin, which produce different artifacts.

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

Usage Guidelines3/5

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

Usage is implied by the lifecycle sentence (work against it with any driver, then merge back, undo, or let TTL reclaim), so an agent can infer the workflow. But there is no explicit routing guidance: it never says when to choose this over argon_snapshot_create or argon_pin_sandbox, nor when to use argon_sandbox_discard or argon_sandbox_keep instead of waiting for the TTL.

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