agent-sandbox-platform

validate_sandbox_policy

Check a proposed command against sandbox security policy rules before execution to block denylist matches and egress boundary violations.

Instructions

Evaluates a proposed command against security policy rules (e.g. denylist patterns, egress boundaries) before execution.

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": {
      "command": "<command>"
    },
    "name": "validate_sandbox_policy"
  }
}

Input Schema

Name	Required	Description	Default
`command`	Yes	The command to validate

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Oct 23, 2026

TDQS

B3.3/5.0

Behavior3/5

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

With no annotations, the description carries the full behavioral burden. 'before execution' usefully signals this is a non-executing evaluation, and the examples of rule types clarify what is checked, but nothing is said about the outcome (allow/deny shape, violation details) or whether the call has side effects.

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?

A single front-loaded sentence with no filler; the purpose and rule scope appear immediately. It is appropriately short for a one-parameter tool, though it could afford one more clause on outcomes.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a gate-keeping tool with no annotations and no output schema, the description omits the critical piece: what the caller receives (pass/fail verdict, violation list) and how to act on a rejection. An agent cannot wire this into a pre-execution flow based on this text alone.

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 coverage is 100% for the single `command` parameter, so the baseline is 3. The description adds only light context by implying the command is evaluated against policy patterns, without clarifying format expectations (full command line vs. binary) or quoting rules.

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 (Evaluates) and resource (a proposed command) plus the criteria domain (security policy rules such as denylist patterns and egress boundaries). It is clearly distinguishable from execute_in_sandbox in spirit, though the sibling is never named to make the contrast explicit.

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?

'before execution' implies this is a pre-flight check, which hints at when to call it, but the description never names execute_in_sandbox as the follow-up step, nor states what to do when validation fails. Usage is inferable rather than prescribed.

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

Deploy Server