rent.dev

Terminate a sandbox

rent_terminate_sandbox

DestructiveIdempotent

Ends a sandbox now, deleting its memory and files, and settles its charge. Terminating an ended sandbox answers it unchanged. The id keeps answering rent_get_sandbox.

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": {
      "sandbox_id": "<sandbox_id>"
    },
    "name": "rent_terminate_sandbox"
  }
}

Input Schema

Name	Required	Description	Default
`sandbox_id`	Yes	Sandbox id (`lse_…`) from rent_create_sandbox or rent_list_sandboxes. It names the sandbox for its whole life and keeps answering rent_get_sandbox, with the final state, after it ends.

Output Schema

Name	Required	Description	Default
`id`	Yes
`wire`	Yes
`state`	Yes
`domain`	Yes
`region`	Yes
`ended_at`	Yes
`metadata`	Yes
`supplier`	Yes
`template`	Yes
`billed_by`	Yes
`cpu_count`	Yes
`memory_mb`	Yes
`account_id`	Yes
`auto_pause`	Yes
`created_at`	Yes
`sandbox_id`	Yes
`started_at`	Yes
`timeout_at`	Yes
`auto_resume`	Yes
`endpoint_id`	Yes
`held_micros`	Yes
`captured_micros`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare destructive/idempotent/openWorld, but the description adds real substance beyond them: exactly what is destroyed (memory and files), that billing is settled at termination, and that a repeat call is a harmless no-op returning unchanged. What is left unsaid is whether a paused sandbox can also be terminated and whether the return payload differs on the no-op path.

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, front-loaded with the action and its destructive scope, then idempotency, then id persistence. No filler and nothing repeated that the schema already states verbatim.

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?

An output schema exists, so return values need no explanation, and for a one-parameter destructive mutation the description covers destruction, billing settlement, and repeat-call behavior. It is nearly complete; only the interaction with the paused state is unaddressed.

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?

Only one parameter and schema coverage is 100%, so the schema already documents the id fully. The description adds the useful post-termination fact that the id remains valid for rent_get_sandbox, but contributes no format or sourcing detail beyond the schema.

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?

Specific verb+resource ('Ends a sandbox now') with concrete consequences spelled out: memory and files are deleted and the charge is settled. It is clear against pause/resume-style siblings by implication of deletion, though it never names a contrasting sibling explicitly.

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 rather than stated: it is the action to take when a sandbox should not continue running, and the no-op behavior on an already-ended sandbox tells the agent not to check state first. There is no explicit when-to-use/when-not guidance or routing to rent_pause_sandbox for reversible cases.

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

All rent.dev tools Inspect

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

Need Help?