Execute code in an isolated sandbox. Supports Python, JavaScript, TypeScript, and Bash. Returns stdout/stderr, the probed interpreter version, and any files the code wrote (base64, under size/count caps).
| 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 declare the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true), so the bar is lower, and the description adds real context: what comes back (stdout/stderr, probed interpreter version, written files as base64) and that file capture is bounded by size/count caps. It still omits timeout enforcement behavior, network isolation guarantees, and failure semantics for package installs.
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?
Three tight sentences, front-loaded with the core action, then capabilities, then return shape. No filler or repetition.
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 no output schema, the description carries the return-value burden and does so by naming stdout/stderr, interpreter version, and captured files with caps. It is nearly complete, missing only error/timeout behavior and package-install failure handling.
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 description coverage is 100%, so the schema already documents all five parameters including the language enum, packages, files, and timeout. The description only echoes the language list and return payload, adding no syntax or format detail beyond the schema, so the baseline 3 applies.
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?
States a specific verb and resource ('Execute code in an isolated sandbox') and enumerates supported languages, so the agent knows exactly what the tool does. It does not distinguish itself from related siblings like scalix_computer_exec or scalix_fn_invoke, which also run code, so it stops short of a 5.
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?
There is no when-to-use guidance and no mention of alternatives, even though several siblings (scalix_computer_exec, scalix_fn_invoke, scalix_build_create) overlap with running code. Usage is only implied by the name.
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.