Executes a workspace Python file inside an isolated Docker container with no network, limited CPU/memory, and a 10-second timeout to safely run untrusted code.
Run a Python file from the workspace in an isolated Docker container (no network, limited CPU/memory, 10s timeout).
| Name | Required | Description | Default |
|---|---|---|---|
| path | Yes |
Changes observed during successful MCP inspections.
v0.1.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses the isolation model (Docker), the absence of network, CPU/memory limits, and a 10s timeout — all traits an agent needs before invoking. It stops short of saying what happens on timeout (killed? error returned?) or what gets returned (stdout, exit code), which matters for a process-execution tool.
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?
A single sentence, front-loaded with the action and then the environment constraints. Every clause carries information; nothing is padding.
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?
The invocation-side context (sandbox, network, limits, timeout) is complete, but there is no output schema and the description says nothing about return values — an agent cannot tell whether it gets stdout, stderr, an exit code, or just success/failure, which is a meaningful gap for an execution tool.
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?
Only one parameter exists and schema coverage is 0%, so the description must compensate. 'From the workspace' implies the path is workspace-relative, which is a useful hint, but it never clarifies whether absolute paths are accepted or whether the file must already exist.
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 (Run) plus resource (a Python file from the workspace) and immediately scopes it to an isolated Docker container. No sibling does execution, so it is trivially distinguishable from list_files/read_file/write_file/query_db.
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?
Usage is implied by 'Python file from the workspace' and by the sandbox constraints (no network, 10s), which hint at what is appropriate to run. However, it never says when to prefer this over alternatives or what preconditions apply (file must already exist; use write_file first).
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.