rent.dev

Terminate a GPU pod

rent_terminate_gpu_pod

DestructiveIdempotent

Ends a GPU pod on RunPod, deleting its container disk, and stops RunPod's billing. Terminating an ended pod answers it unchanged.

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": {
      "pod_id": "<pod_id>"
    },
    "name": "rent_terminate_gpu_pod"
  }
}

Input Schema

Name	Required	Description	Default
`pod_id`	Yes	GPU pod id (`lse_…`) from rent_create_gpu_pod or rent_list_gpu_pods; valid until the pod is terminated, and listed after with its final state.

Output Schema

Name	Required	Description	Default
`id`	Yes
`name`	Yes
`image`	Yes
`ports`	Yes
`state`	Yes
`pod_id`	Yes
`ended_at`	Yes
`gpu_type`	Yes
`billed_by`	Yes
`gpu_count`	Yes
`volume_gb`	Yes
`account_id`	Yes
`cloud_type`	Yes
`created_at`	Yes
`started_at`	Yes
`credential_id`	Yes
`container_disk_gb`	Yes
`cost_per_hour_usd`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 12, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=true, but the description adds concrete consequences beyond them: container disk deletion and RunPod billing cessation. It also explains the idempotent outcome in plain language ("answers it unchanged"), which is genuinely useful context for a destructive call.

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 compact sentences with the destructive effect front-loaded. The phrasing "answers it unchanged" is slightly awkward but still informative and avoids unnecessary exposition.

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 not be described. Given the annotations and 100% schema coverage, the description supplies the essential destructive-effect and idempotency context; only explicit permission or data-loss warnings are missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% and the sole parameter pod_id is fully described in the schema, including its origin and lifecycle. The description adds no parameter-specific detail, so the schema is doing the heavy lifting; a baseline score is appropriate.

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 and resource ("Ends a GPU pod on RunPod") and immediately clarifies scope with the disk-deletion and billing side effects. An agent can distinguish this from rent_create_gpu_pod or rent_terminate_sandbox without opening another schema.

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 name and verb – call this to end an existing pod. There is no explicit when-to-use versus alternatives or prerequisites, though the second sentence clarifies behavior on an already-ended pod.

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?