Skip to main content
Glama
Sign In
BitPull

BitPull

by SamuealPK
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

use_open_model

Run open AI models for image, audio, speech, OCR, translation, embedding, and reranking tasks on your own network computers for free or on community machines using credits.

Instructions

Run an open model on one of the person's network computers (free) or on a community computer (paid in credits). The computer that runs it can read the request: use placement mine for private data. Tasks: image (prompt, count, size), upscale (file), stt (file: WAV), tts (text, voice), music (prompt, lyrics, seconds), vision (file + prompt), ocr (file), translate (text, targetLanguage), embed (text: string or list), rerank (query, documents). Files must be in a folder authorised in BitPull. Images and audio are saved as files and their paths returned. For plain chat use ask_open_model.

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": {
      "task": "<task>"
    },
    "name": "use_open_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoAbsolute path of the input image (PNG/JPEG) or audio (WAV)
sizeNo
taskYes
textNo
countNo
modelNoModel id from list_open_models; omitted = the most available one for the task
queryNo
voiceNo
lyricsNo
promptNo
secondsNo
languageNo
documentsNo
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.
waitMinutesNoHow long to wait; default: the person's setting, at least 30 minutes for images and music
targetLanguageNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the burden and does well: it discloses the cost model (free vs paid credits), the privacy exposure ('the computer that runs it can read the request'), the authorization prerequisite, and that image/audio outputs are written to files with paths returned. It does not cover timeout/failure behavior or queueing despite offering a waitMinutes control.

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 capability, cost, and the privacy warning, then a compact per-task enumeration that packs a lot into one sentence. The task list is dense but readable; a small amount of formatting loss is the price of the compression.

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 16-parameter, annotation-free, no-output-schema tool, the definition covers purpose, cost, privacy, per-task parameters, file prerequisites, and the return shape for file-producing tasks. Remaining gaps are the undocumented 'language' field and the return shape for non-file tasks (embed vectors, rerank scores), which matter given no output schema exists.

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

Parameters5/5

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

Schema coverage is only 25% across 16 parameters, so the description must compensate, and it does by mapping each task to its relevant inputs (image: prompt/count/size; stt: WAV file; tts: text/voice; music: prompt/lyrics/seconds; rerank: query/documents; translate: text/targetLanguage). This tells an agent which fields matter per task, which the raw enum and untyped properties do not. Only the 'language' parameter is never accounted for.

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?

Opens with a specific verb and resource ('Run an open model on one of the person's network computers') and immediately names the scope distinction (free own-network vs paid community). It also explicitly separates itself from the sibling ask_open_model for plain chat, so an agent can route without opening either schema.

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

Usage Guidelines4/5

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

Gives concrete routing rules: use placement 'mine' for private data, 'auto' for free-first-then-community, and use ask_open_model instead for plain chat. It also states the prerequisite that files must sit in a folder authorised in BitPull. No explicit when-not-to-use conditions beyond the chat alternative, which keeps it short of a 5.

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