skypilot-mcp

skypilot_volume_apply

Create or register a cloud volume by name and type, such as k8s-pvc or runpod-network-volume, with an optional size, infra, and labels. Returns a request_id to track the volume provisioning.

Instructions

Create or register a volume. Accepts a volume configuration as a JSON/dict with fields: name, type ('k8s-pvc' or 'runpod-network-volume'), size (e.g. '100GB'), and optional fields like infra, labels, use_existing, config. Returns a request_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": {
      "name": "<name>",
      "volume_type": "<volume_type>"
    },
    "name": "skypilot_volume_apply"
  }
}

Input Schema

Name	Required	Description	Default
`name`	Yes
`size`	No
`infra`	No
`config`	No
`labels`	No
`volume_type`	Yes
`use_existing`	No

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 13, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already declare destructiveHint=false and openWorldHint=true, so the safety profile is partly covered. The description adds that it 'Returns a request_id', hinting at an async workflow, but it does not say the caller must poll via skypilot_get_request, nor does it state permission or idempotency behavior for the 'register' path.

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 followed by the parameter inventory; nothing is wasted. The field list is dense but each item earns its place given 0% schema coverage.

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?

Output schema exists, so the return value need not be explained in depth, and the description's brief request_id note suffices. For a mutating operation with 0% schema coverage, it covers the parameters adequately, though it omits the async follow-up step and register-vs-create semantics.

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 description coverage is 0%, so the description must carry the load, and it does: it enumerates all fields (name, type, size, infra, labels, use_existing, config), marks the optional ones, and supplies enum-like values for type and a size example ('100GB') not present in the schema. Minor gap: the distinction between volume_type and the described 'type' field could confuse.

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?

States a specific verb+resource ('Create or register a volume') that an agent can clearly distinguish from skypilot_volume_ls, skypilot_volume_delete, and skypilot_volume_validate. It does not explicitly name those siblings, but the create verb makes the role unambiguous.

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?

Implied usage is clear from 'Create or register', but there is no explicit guidance on when to use this versus skypilot_volume_validate (validation first?) or when to prefer registering vs creating. No when-not or prerequisite information is given.

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

Deploy Server