Skip to main content
Glama
Sign In
BitPull

BitPull

by SamuealPK
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

run_job

Run sandboxed commands on available network computers or community machines, with encrypted transfer, isolation, and automatic deletion after results are returned.

Instructions

Run a command in a sandbox on one of the person's own network computers if one is free, otherwise on another BitPull user's computer (encrypted on the way, no network, isolated, deleted afterwards; the computer that runs it can read the job, so use placement mine for private data). Put small input files in inputs (path -> base64). For large files of any kind (video, datasets, archives…) use files (path in the job -> file on this computer, inside a folder the person authorised): they are encrypted here and sent directly, with no fixed size limit; call bitpull_file_limits first to see how much one job can carry right now. Files written to /work/out come back in the result; large ones are saved into outputFolder. Prefer several smaller jobs to one huge job when the work can be divided (one file or one segment per job): the result is the same and the parts run in parallel on several computers. Everything is deleted from the computer that ran the job as soon as the result is delivered. Costs BitPull credits.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "image": "<image>",
      "command": "<command>"
    },
    "name": "run_job"
  }
}

Input Schema

NameRequiredDescriptionDefault
cpusNo
waitNoWait for the result (default true; up to 2 minutes, or 6 hours when large files are sent)
filesNoLarge input files: path inside the job -> absolute path on this computer (inside an authorised folder)
imageYesPublic container image, e.g. python:3.12-slim
inputsNo
commandYes
memoryMbNo
isolationNovm: only computers that run each job in its own virtual machine
placementNoauto (default): the person's own network computers first, for free, then the community. mine: never leaves the person's own computers; use it for private data.
timeoutSecNo
outputFolderNoAuthorised folder where large results are saved (then deleted from BitPull's store)
deterministicNoTrue if the same inputs always give the same output

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior4/5

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

Annotations only declare openWorldHint, so the description carries the burden and delivers: encryption in transit, no network, isolation, deletion after delivery, the caveat that the host computer can read the job, and that it costs credits. It does not explain what happens when 'wait' is false or how to retrieve results later, which is the remaining behavioral gap.

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

Conciseness4/5

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

Front-loaded with the core action and the safety-critical placement caveat before the operational details. It is a dense run-on paragraph with stacked parentheticals, but nearly every clause carries information an agent needs, so little is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter, no-output-schema execution tool, it covers the input-file mechanics, output retrieval via /work/out and outputFolder, and parallelization strategy. It leaves open how results are obtained when wait=false and what the result payload actually contains, which matters given no output schema exists.

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

Parameters4/5

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

Schema coverage is 58%, and the description compensates strongly for the most consequential parameters: the inputs-vs-files distinction, the /work/out to outputFolder return path, and the privacy semantics of 'placement mine'. It adds little for cpus, memoryMb, timeoutSec, or deterministic, which are left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a concrete verb and resource — 'Run a command in a sandbox' — and immediately scopes where it runs (own network computers first, else another user's computer). It is clearly a remote sandboxed execution tool, distinguishable from siblings like job_status or bitpull_site_job without inspecting schemas.

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

Usage Guidelines5/5

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

Explicit routing rules are given: use 'placement mine' for private data, use 'inputs' for small files and 'files' for large ones, call bitpull_file_limits first, and split work into several smaller jobs rather than one huge job. These are concrete when-to-use and when-not-to-use instructions with named alternatives.

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

Deploy Server

Other Tools