Skip to main content
Glama
aliyun-agent-sandbox-mcp

aliyun-agent-sandbox-mcp

Create a sandbox

sandbox_create

Create an Alibaba Cloud Agent Sandbox and return its sandbox_id so it can be reused in later tool calls; configure TTL, template, env vars, and metadata, then kill it when finished.

Instructions

Create a new Alibaba Cloud Agent Sandbox (阿里云智能体沙箱) and return its sandbox_id. Keep the ID to reuse the sandbox in later tool calls, and call sandbox_kill when done. Defaults to the code-interpreter-v1 template with a 5 minute TTL.

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": "sandbox_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
envsNoEnvironment variables injected into the sandbox.
metadataNoFree-form key/value metadata stored on the sandbox.
templateNoTemplate name or ID. Defaults to E2B_TEMPLATE / code-interpreter-v1.
timeout_msNoSandbox TTL in milliseconds. Defaults to SANDBOX_TIMEOUT_MS (300000 = 5 minutes).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only supply openWorldHint=true and destructiveHint=false, so the description carries the substantive burden and does so well by disclosing the default template (code-interpreter-v1) and the 5-minute TTL. It still omits whether creation consumes quota, how envs are treated (secrets?), and what happens on template-not-found, but the core defaults are surfaced.

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 tight sentences: the action and return value come first, then lifecycle guidance, then defaults. Every clause carries information an agent needs, with no padding.

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?

With no output schema, stating that the tool returns sandbox_id is the key missing piece an agent would otherwise lack, and it is provided along with TTL and template defaults. Only edge-case behavior (quota, failure modes) is unaddressed, which is minor for a creation tool with fully described parameters.

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%, including defaults for template and timeout_ms, so the description repeats rather than extends the parameter meanings. It adds no guidance on envs or metadata, which is acceptable given the baseline for fully documented schemas.

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?

The description names a specific verb (create) and resource (Alibaba Cloud Agent Sandbox), states the return value (sandbox_id), and explicitly routes cleanup to the sibling tool sandbox_kill. An agent can tell this is the creation entry point for the sandbox family without opening any schema.

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

Usage Guidelines4/5

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

The description gives clear lifecycle guidance: retain the returned ID for later calls and invoke sandbox_kill when finished. It does not discuss reusing an already-running sandbox (e.g., via sandbox_list) before creating a new one, so the when-not-to-create condition is left implicit.

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