Skip to main content
Glama
Sign In

ce-net

by com.ce-net
OverviewDiscussionsAdmin

run_code

Run a program once in a sandbox on a spare ce-net machine (no network, no shell, only its own...

Input Schema

NameRequiredDescriptionDefault
filesNo
publicNo
commandYes
timeout_sNo
result_pathNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added
  4. Removed
  5. Added
  6. Removed
  7. Added
  8. Removed
  9. Changed6 schema fields changed
    • removedInput schema / properties / command / items / properties
      Removed value: -null
    • removedInput schema / properties / command / properties
      Removed value: -null
    • removedInput schema / properties / files / properties
      Removed value: -null
    • removedInput schema / properties / public / properties
      Removed value: -null
    • removedInput schema / properties / result_path / properties
      Removed value: -null
    • removedInput schema / properties / timeout_s / properties
      Removed value: -null
  10. Changed11 schema fields changed
    • removedInput schema / properties / command / description
      Removed value: -"argv, e.g. [\"python3\", \"sim.py\"]; never a shell string"
    • addedInput schema / properties / command / items / properties
      Added value: +null
    • addedInput schema / properties / command / properties
      Added value: +null
    • removedInput schema / properties / files / description
      Removed value: -"relative path -> text content, put in the job folder (source only, no binaries)"
    • addedInput schema / properties / files / properties
      Added value: +null
    • removedInput schema / properties / public / description
      Removed value: -"true lets any machine on the network run it, including ones that joined self-serve; leave false for work you would not show a stranger"
    • addedInput schema / properties / public / properties
      Added value: +null
    • removedInput schema / properties / result_path / description
      Removed value: -"file the job writes its answer to, default result.json; it comes back as output"
    • addedInput schema / properties / result_path / properties
      Added value: +null
    • removedInput schema / properties / timeout_s / description
      Removed value: -"seconds, default 120; the cap depends on your account's level (compute_backends)"
    • addedInput schema / properties / timeout_s / properties
      Added value: +null
  11. Added

TDQS

C2.6/5.0
Behavior3/5

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

The description adds useful sandbox constraints beyond the annotations: no network, no shell, one-time execution on a spare machine. These clarify the execution environment. However, it is truncated ('only its own...') and does not explain result retrieval, timeout behavior, or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one incomplete sentence ending in an ellipsis. It is short but under-specified rather than concise, leaving critical information missing.

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 code-execution tool with no output schema and five undocumented parameters, the description is far too thin. It states basic sandbox constraints but omits how inputs map to execution, how results are returned, and how this differs from related execution tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters1/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% for five parameters, including a nested files object, public flag, timeout, and result_path. The description does not mention any parameter or explain how to pass the command, files, or retrieve results. It fails to compensate for the schema gap.

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?

The description states a specific verb and resource: 'Run a program once in a sandbox on a spare ce-net machine.' An agent can infer this executes code in an isolated environment. However, it does not distinguish this from sibling tools like code_call, host_code, or compute_submit, and the description is truncated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit guidance on when to use this tool versus alternatives such as code_call, compute_submit, or host_code. The phrase 'once' and sandbox constraints imply a one-off execution context, but the agent is left to infer selection criteria.

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

All ce-net toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources