Skip to main content
Glama
Podcast MCP
by calebn

model_download

Downloads a required Whisper, RNNoise, word-aligner or speaker model after your approval, letting agents fetch missing podcast transcription and audio-processing components.

Instructions

Download one model, only after the user agrees: ask first, never call this on your own.

component is the model.id of a model_needed refusal (whisper, rnnoise, word-aligner or speaker-ecapa); whisper_model picks the Whisper size and upgrade re-fetches a model that no longer matches its pin. Inside the ShareCut Studio process (this server reached through Studio's own MCP endpoint) it starts a download job and returns its job_id: poll model_download_status. In any other server, including a stdio server next to a running Studio (this tool is not handed to Studio, as it has no project_path), it downloads in this call, which can take minutes for Whisper, reports progress while it runs, and starts no job, so model_download_status answers {"running": false} and Studio does not see it.

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": {
      "component": "<component>"
    },
    "name": "model_download"
  }
}

Input Schema

NameRequiredDescriptionDefault
upgradeNo
componentYes
whisper_modelNo

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.1.4

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does most of it: it discloses the consent requirement, the two execution modes (job + job_id vs. synchronous in-call download), that Whisper downloads can take minutes, that progress is reported mid-call, and that Studio does not see out-of-process downloads. It omits failure/partial-download behavior, disk requirements, and whether concurrent or repeated downloads are safe.

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-loads the consent rule, which is the highest-stakes instruction, and the rest is dense rather than padded. The nested parenthetical about the stdio server lacking ``project_path`` is harder to parse than it needs to be, but it conveys real information about the deployment split.

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 three-parameter tool with an output schema (so return values need no explanation) and no annotations, the description covers purpose, consent, parameter values, and the divergent runtime behaviors. What remains thin is error handling and resource expectations (disk, retries) for a potentially multi-minute download.

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 0%, so the description must compensate and does: it defines ``component`` as the ``model.id`` from a ``model_needed`` refusal and enumerates the four valid values, explains ``whisper_model`` selects Whisper size, and explains ``upgrade`` re-fetches a model that no longer matches its pin. All three parameters gain meaning absent from 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?

Opens with a specific verb and resource ("Download one model") and immediately names the sibling it pairs with (model_download_status) as well as the refusal source it responds to (model_needed). An agent can tell this apart from the status-polling sibling 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 Guidelines5/5

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

Gives an explicit precondition ("only after the user agrees: ask first, never call this on your own") plus the post-call routing rule (poll model_download_status inside Studio, expect a blocking call elsewhere). It also states when not to expect a job, which is exactly the decision an agent needs before invoking.

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