Skip to main content
Glama
Sign In
Pavo 官网 MCP

Pavo 官网 MCP

by congliu1851-ui
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

关联已上传媒体到片段

pavo_script_attach_segment_media
Idempotent

Attaches uploaded image or video to a script segment's media slot by verifying fingerprint, preserving script text and other media without generating new content.

Instructions

将已上传HTTPS图片/视频沿原生media/upload存历史，再select并回读槽位；image用segment_keyframe，video用segment_video且须明确first_frame_url。核最新media指纹，保护脚本文字和其它媒体。不生图、不生成视频；部分成功保持UNKNOWN，禁止换号重投。

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": {
      "project_id": "<project_id>",
      "episode_id": "<episode_id>",
      "segment_id": "<segment_id>",
      "media_type": "<media_type>",
      "url": "<url>",
      "expected_sha256": "<expected_sha256>",
      "operation_id": "<operation_id>"
    },
    "name": "pavo_script_attach_segment_media"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
episode_idYes
media_typeYes
project_idYes
segment_idYes
operation_idYes
thumbnail_urlNo
expected_sha256Yes
first_frame_urlNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.3.1

TDQS

A3.8/5.0
Behavior5/5

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

Beyond the annotations it discloses real behavior: history is written along the native media/upload path, the slot is selected and read back, existing script text and other media are protected, and partial success must remain UNKNOWN. The no-account-switch retry rule and fingerprint verification add operational constraints the annotations do not convey, and none of it contradicts readOnly=false, idempotent=true, destructive=false.

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 purpose is front-loaded in the first clause and every clause carries information with no filler. The telegraphic, jargon-dense phrasing ('沿原生media/upload存历史', '回读槽位') compresses readability more than necessary, but 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?

An output schema exists, so return values need no explanation, and the risky behaviors (partial success, UNKNOWN state, retry policy) are covered. However, for a nine-parameter mutation tool with zero schema descriptions and openWorldHint=true, five parameters are left entirely unexplained, which is a real gap.

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 0% across nine parameters, so the description carries the burden and it does explain the non-obvious ones: url must be HTTPS, media_type maps to segment_keyframe vs segment_video, first_frame_url is mandatory for video, and expected_sha256 verifies the latest media fingerprint. It says nothing about project_id, episode_id, segment_id, operation_id or thumbnail_url, so half the surface remains undocumented.

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 description states a specific verb and resource: attach already-uploaded HTTPS image/video onto a segment slot via the native media/upload path, then select and read back. It also distinguishes itself from generation siblings by explicitly saying it does not generate images or videos. It stops short of naming the sibling that does generate (submit_segment_video), so a 4 rather than 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 Guidelines3/5

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

Use is implied by prerequisites: media must already be uploaded and served over HTTPS, with image routed to segment_keyframe and video to segment_video plus a mandatory first_frame_url. Retry guidance is present ('禁止换号重投'), but the description never names an alternative tool for the generate-media case, leaving the agent to infer the boundary from the sibling list.

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