Skip to main content
Glama

video_extend

视频延长(在源视频末尾追加 N 秒)

仅支持 seedance-2.0 模型基座。 源视频二选一:workspace_id(内部)或 video_url(外部);同时传 / 同时空均报错。 duration 为增量秒数:原 8s + duration=4 → 输出 12s。

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": "video_extend"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNo仅支持 `seedance-2.0`。seedance-2.0
ratioNo
promptNo
durationNo必填。在源视频末尾追加的秒数,范围 4~15;不传或传 0 返回 `ret=10000`。
video_urlNo
resolutionNo
callback_idNo自定义追踪 ID,会在 `/openapi/v1/work/status` 的结果里原样回传,用于对回你自己的业务单号(暂不支持 webhook 推送)
workspace_idNo
idempotency_keyNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / description
      Previous value: -"视频延长。源视频二选一:`workspace_id`(内部)或 `video_url`(外部);同时传 / 同时空均报错。\n`duration` 为增量秒数。\n\n**仅支持 `seedance-2.0` 模型基座**,不开放其他模型。`duration` 取值范围 4~15(默认 15),`resolution` 取 `720p` / `1080p`。\n"New value: +"视频延长。源视频二选一:`workspace_id`(内部)或 `video_url`(外部);同时传 / 同时空返回 `ret=10000`(`msg` 为 `Invalid parameters`),不扣积分。\n`duration` 为增量秒数。\n\n**仅支持 `seedance-2.0` 模型基座**,不开放其他模型:传其他值返回 `ret=10000`,`msg` 为 `unsupported model \"<传入值>\" for video edit / extend; supported models: seedance-2.0`。`duration` 必填,取值 4~15,超出会调到最近的上限 / 下限;`resolution` 取 `720p`(默认)/ `1080p` / `480p` / `4k`。\n"
    • changedInput schema / properties / callback_id / description
      Previous value: -"自定义追踪 ID,webhook URL 后台配置"New value: +"自定义追踪 ID,会在 `/openapi/v1/work/status` 的结果里原样回传,用于对回你自己的业务单号(暂不支持 webhook 推送)"
    • changedInput schema / properties / duration / description
      Previous value: -"在源视频末尾追加的秒数;范围 4~15,默认 15。"New value: +"必填。在源视频末尾追加的秒数,范围 4~15;不传或传 0 返回 `ret=10000`。"
    • changedInput schema / properties / resolution / enum
      Previous value: -[
      -  "720p",
      -  "1080p"
      -]New value: +[
      +  "720p",
      +  "1080p",
      +  "480p",
      +  "4k"
      +]
  2. First observed

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare the mutation/safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=true). The description adds genuinely new behavioral facts: the model base is restricted and simultaneous/absent source params produce an error. It does not disclose that this is a long-running job requiring status polling, nor how idempotency_key affects retries.

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?

Three short front-loaded statements: purpose, model restriction, source-selection rule, then the duration semantics. Nearly every sentence earns its place, with only mild duplication against the input-schema description.

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?

For a 9-parameter mutation tool with no output schema and 33% schema coverage, the description covers the critical decision points but leaves a third of the surface (resolution, ratio, prompt, callback_id, idempotency_key) undocumented. It also omits the async result-retrieval flow, which an agent needs to complete the task.

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 coverage is only 33%, so the description must carry weight, and it does for the two decisive parameters: it explains workspace_id vs video_url as a strict either/or (both or neither errors) and clarifies duration as an increment with a worked example (8s + 4 = 12s). ratio, prompt, resolution, idempotency_key and callback_id remain unexplained in both places, keeping it below 5.

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 gives a specific verb and resource plus the exact operation semantics: '视频延长(在源视频末尾追加 N 秒)'. That makes it distinguishable from generic editing siblings such as video_edit without naming them. It stops short of explicitly contrasting itself with any sibling, so it is a strong 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?

Usage context is implied by 'append N seconds to the end of the source video' and reinforced by hard constraints (only seedance-2.0, exactly one of workspace_id/video_url). However, there is no explicit when-not guidance or named alternative (e.g. video_edit) for an agent that is unsure whether to extend versus re-edit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources