Execute code in an isolated sandbox. Supports Python, JavaScript, TypeScript, and Bash. Returns stdout/stderr.
| Name | Required | Description | Default |
|---|---|---|---|
| code | Yes | Source code to execute | |
| files | No | Additional files (filename -> content) | |
| language | Yes | Programming language | |
| packages | No | Packages to install (pip/npm) | |
| timeout_seconds | No | Max execution time in seconds (default: 30) |
Changes observed during successful MCP inspections.
Input schema / properties / language / enumPrevious value: -[
- "python",
- "javascript",
- "typescript",
- "go",
- "rust",
- "bash"
-]New value: +[
+ "python",
+ "javascript",
+ "typescript",
+ "bash"
+]Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide safety profile (readOnly=false, openWorld=true). The description adds the 'isolated' context and return of stdout/stderr, which is useful, but it doesn't disclose potential side effects or network access nuances. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the primary action, and contains no fluff. Every word adds value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With a rich schema covering all parameters and no output schema, the description provides return behavior (stdout/stderr) and execution context. It doesn't explain files or packages relationships, but schema handles those details, making it sufficiently complete for the tool's complexity.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so all parameters are already documented. The description adds no extra meaning beyond what the schema provides, aligning with the baseline of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool executes code in an isolated sandbox, with a specific verb and resource. It lists supported languages and differentiates from siblings like scalix_computer_exec or scalix_fn_invoke by emphasizing isolation and language support.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The context of an isolated sandbox implies safe, throwaway code execution, but no explicit when-to-use alternatives or exclusions are given. It doesn't mention when to prefer this over scalix_computer_exec or scalix_fn_invoke, so usage is only implied.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.