Skip to main content
Glama

thanaton_run_code

Execute a standalone, single-file code snippet in an ephemeral, stateless microVM sandbox that is automatically destroyed after execution, isolating code from the local machine.

Instructions

Directly run a standalone, single-file code snippet in an ephemeral, stateless microVM sandbox (automatically destroyed after execution). For stateful multi-step terminal interactions, filesystem persistence, or long-running processes, use 'thanaton_spawn_sandbox' followed by 'thanaton_exec_command' passing the 'sandbox_id'.

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": {
      "language": "<language>",
      "code": "<code>"
    },
    "name": "thanaton_run_code"
  }
}

Input Schema

NameRequiredDescriptionDefault
codeYesThe complete source code snippet to compile and execute
languageYesProgramming language runtime
timeout_msNoTimeout in milliseconds (default: 10000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.6

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations provided, the description carries the full behavioral burden and does disclose the key traits: ephemeral, stateless, and destroyed after execution, which tells the agent nothing persists. It does not state what the call returns (stdout, stderr, exit code) despite there being no output schema, nor whether the sandbox has network access or resource limits.

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 padding, with the core capability front-loaded and the routing guidance second. Every clause carries information an agent needs to choose or call the tool.

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?

For a three-parameter execution tool with no annotations, the description covers environment nature, lifecycle, and sibling routing well. The remaining gap is the absence of any statement about what a run returns or how failures surface, which matters since no output schema exists.

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 language, code, and timeout_ms are already documented in the schema, and the description adds no syntax or format guidance for them. The phrase "single-file" implies the code parameter must be self-contained, which is a small but real addition; baseline 3 applies.

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?

States a specific verb+resource ("run a standalone, single-file code snippet") plus the execution environment ("ephemeral, stateless microVM sandbox") and its lifecycle ("automatically destroyed after execution"). This distinguishes it clearly from siblings like thanaton_spawn_sandbox and thanaton_exec_command without needing their schemas.

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

Usage Guidelines5/5

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

Explicitly names the alternatives ("thanaton_spawn_sandbox" followed by "thanaton_exec_command" with "sandbox_id") and the exact conditions that select them: stateful multi-step terminal interactions, filesystem persistence, or long-running processes. That is a complete when/when-not routing rule.

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