Skip to main content
Glama

vidlens_models

List, recommend, download, and track local models for on-device video analysis, including hardware suitability, download size/location, and status checks without repeating downloads.

Instructions

本地模型目录 / 硬件建议 / 下载(大小、落点、换目录都说清)。 action=list 看目录(含本机解析出的真实路径);action=recommend 看这台机器适合哪个; action=download 装某个模型:先只报大小与落点,传 confirm=true 才真下; action=status 看下载是否还在跑(客户端超时后用它,别重复发第二次下载)。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "vidlens_models"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameNo
actionNolist
confirmNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.6.3

TDQS

A4.5/5.0
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: download is two-phase (report size/location first, only confirm=true actually downloads), and status exists because downloads outlive client timeouts. It does not cover permissions, cancellation, or disk-space preconditions, so it is not fully complete.

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?

The action-to-purpose mapping is front-loaded and each clause carries information, with the destructive-ish download flow called out in bold. It is dense but every sentence earns its place; minor compression could tighten the parentheses around real local paths.

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?

No output schema exists, yet the description signals what list returns (including resolved real local paths) and what status reports (whether the download is still running). Missing only edge cases like failure handling or size units, which are secondary for a 3-parameter tool.

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 description coverage is 0%, so the description must compensate. It defines the four action values and the confirm semantics clearly, and only implies that name identifies the model to install ('装某个模型') without stating expected format or that it is ignored for non-download actions.

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 three concrete resources (local model catalog, hardware advice, downloads) and then enumerates each action verb (list/recommend/download/status) with its purpose. An agent can tell immediately that this is the model-management tool, distinct from the video-processing siblings such as video_meta or video_plan.

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?

It routes per action explicitly: list to see the catalog, recommend for this machine, download to install, status to check an in-flight download. It even gives an exclusion rule ('after a client timeout use status, don't fire a second download'), which is exactly the when/when-not guidance required.

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