Run agent code (python / javascript / bash) in an isolated sandbox (no network, CPU/RAM/time limits) and get stdout/stderr/exit_code back. Charged from agent balance; returns payment_required if insufficient (then topup_balance and retry).
| Name | Required | Description | Default |
|---|---|---|---|
| code | No | ||
| timeout | No | ||
| agent_id | Yes | ||
| language | No | python |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Since no annotations are provided, the description carries full burden. It discloses that execution happens in an isolated sandbox with no network, CPU/RAM/time limits, and that charges apply. This gives the agent a good understanding of important behavioral traits such as resource constraints and billing.
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 long, with the first sentence clearly stating the action and output, and the second addressing billing. Every word adds value. It is front-loaded with the core functionality.
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?
Given the complexity (4 parameters, no output schema, no annotations), the description covers essential aspects: purpose, sandbox constraints, return values, and billing. It lacks details on parameter formats or default values, but the overall information is sufficient for using the tool correctly.
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?
The schema coverage is 0% (no parameter descriptions), so the description must add meaning. It mentions supported languages ('python / javascript / bash'), which relates to the 'language' parameter, and implies that 'code' is executed and 'timeout' affects runtime. However, it does not explicitly describe each parameter's format or constraints, leaving some gaps.
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 what the tool does: run agent code in a sandboxed environment. It specifies supported languages (python, javascript, bash) and what is returned (stdout, stderr, exit_code). This distinguishes it from sibling tools like fetch_web or check_balance, which have different purposes.
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 description explains that running code costs agent balance and returns 'payment_required' if insufficient, with a suggestion to top up and retry. This provides clear context for when to use the tool and what to do if balance is low. It does not explicitly state scenarios where the tool should not be used, but the context implies it's for executing code.
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.
Most tools have distinct purposes, but fetch_ru and fetch_web overlap in functionality (fetch_ru is a specialization). However, descriptions clearly differentiate them.
All tool names follow a consistent verb_noun pattern with snake_case (e.g., check_balance, fetch_web, topup_balance). Minor deviation like run_code is still in line.
9 tools cover the core functionality well without being excessive or insufficient. Each tool has a clear role.
Covers key operations: fetching, proxy, domain management, balance, code execution, and feedback. Missing advanced features like proxy rotation or pagination but sufficient for primary use.