Skip to main content
Glama

thanaton_spawn_sandbox

Provision a hardware-isolated KVM MicroVM or Silicon sandbox for safe code execution, with scale-to-zero, memory snapshots, and optional embedded PostgreSQL.

Instructions

Provision a new hardware-isolated KVM MicroVM or Silicon isolate. Supports scale-to-zero, memory snapshots, and optional embedded PostgreSQL database.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "thanaton_spawn_sandbox"
  }
}

Input Schema

NameRequiredDescriptionDefault
runtimeNoRuntime environment type (default: 'microvm')
with_dbNoWhether to bundle an isolated PostgreSQL database inside the sandbox
memory_mbNoAllocated RAM in MiB (default: 256)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.6

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full behavioral burden. It does disclose genuinely useful traits — hardware-level KVM isolation, scale-to-zero, memory snapshots, and the embedded DB option — but omits whether provisioning is billable, what permissions/auth are needed, what state the sandbox starts in, or any resource limits imposed by memory_mb.

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?

Two sentences, front-loaded with the action and artifact, no filler. The trailing capability list (scale-to-zero, snapshots) is defensible as behavioral context, though it sits between the agent and the decision-relevant details rather than after them.

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?

There is no output schema, so the description should state what provisioning returns — most critically the sandbox identifier that every sibling tool (exec_command, expose_port, destroy_sandbox) will require. It also leaves runtime preconditions and the state of the fresh sandbox unstated, which is a meaningful gap for a zero-required-parameter creation tool.

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 the schema already defines runtime, with_db, and memory_mb, including the default. The description corroborates runtime (MicroVM/Silicon) and with_db (embedded PostgreSQL) but adds no new meaning, and never mentions memory_mb or how allocation interacts with the chosen runtime.

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 description gives a specific verb ('Provision') and resource ('new hardware-isolated KVM MicroVM or Silicon isolate'), so the agent knows this is the creation entry point. It is clearly distinct from destroy/sleep/wake siblings by implication of 'new', but it never names the lifecycle siblings it complements, so differentiation is inferred rather than stated.

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 only implied: the word 'new' signals first-step provisioning, and 'optional embedded PostgreSQL' hints at when to set with_db. There is no explicit when-to-use/when-not guidance, no mention of prerequisites, quotas, or the follow-on tools (exec, expose_port, destroy) an agent should chain to.

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

Deploy Server

Other Tools