Skip to main content
Glama
Sign In
picsense

picsense

by honlnk
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

analyze_video

Extract frames from a video and send them to a vision model to identify content. Use a session ID for follow-up questions in later calls.

Instructions

识别视频内容。把视频抽帧后发送给视觉模型分析（默认每秒抽 1 帧、最多 30 帧）。支持多轮迭代——首次调用创建 session，后续调用传入 session_id 可在已有对话基础上追加提问。

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": {
      "prompt": "<prompt>"
    },
    "name": "analyze_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYes对视频的识别要求，根据当前任务意图编写
session_idNo传入已有 session 的 ID 以发起后续轮次；不传则创建新 session
video_sourceNo视频来源（http URL / 本地文件路径），自动识别。首次调用创建 session 时必填；后续轮次传入 session_id 时可省略（沿用该 session 的视频）

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.3

TDQS

A3.9/5.0
Behavior4/5

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

No annotations exist, so the description carries the full burden, and it discloses meaningful behavior: automatic frame sampling at 1 fps capped at 30 frames, plus stateful session accumulation across calls. It omits cost/latency expectations, session lifetime, and whether video_source is retained server-side, which are relevant for a potentially long-running, stateful call.

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

Conciseness5/5

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

Three compact sentences, each earning its place: purpose and mechanism first, then the iteration model. The parenthetical sampling defaults are dense but useful, and nothing is redundant.

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

Completeness3/5

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

There is no output schema, so the description should characterize the return value; it never says the call yields a session_id (the very handle later calls need) or what the analysis output looks like. Compared to the tool's stateful complexity, this is an important missing piece.

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

Parameters3/5

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

Schema description coverage is 100%, so the schema already documents prompt, session_id, and video_source semantics. The description restates the session round-trip and confirms video_source is only required on session creation, adding no syntax or format detail beyond the schema — baseline 3 is appropriate.

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 first clause names a specific verb+resource (识别视频内容 / recognize video content) and the rest explains the mechanism (frame extraction, vision model). It is clearly distinguishable from analyze_images and analyze_document by resource type, but it never names those siblings or states the boundary explicitly, so it falls short of a 5.

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?

It gives concrete workflow guidance for the stateful pattern: the first call creates a session, later calls pass session_id to append follow-up questions. It does not say when NOT to use this tool (e.g., when to prefer analyze_images for stills) or whether sessions must be cleaned up, so it lacks explicit exclusions.

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