Say It Again

Change a video

change_video

Destructive

Change one finished video as the person asks, made again into a new video beside it, as the app's Change does. This spends the team's credits: the price get_video lists in after_steps as change_video, refunded if it fails. Only for a video whose after_steps offers it. What to change is the person's own words; a change the video cannot be made with at all is answered with why and spends nothing. Answers an id at once: call get_video with it about once a minute until its status is ready or failed.

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": {
      "id": "<id>",
      "change": "<change>",
      "credits": "<credits>",
      "idempotency_key": "<idempotency_key>"
    },
    "name": "change_video"
  }
}

Input Schema

Name	Required	Description
`id`	Yes	The id of a finished video, from make_video or list_videos.
`part`	No	Which of its videos, as get_video names it: v1, the default, v2 and on.
`change`	Yes	What to change, in the person's words, on one line.
`credits`	Yes	The credits after_steps lists for change_video; a different figure is refused.
`idempotency_key`	Yes	Any string unique to this video. Calling again with the same key and the same arguments answers as the first call did and spends nothing more.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 21, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Goes well beyond the annotations by disclosing the credit cost model, the refund-on-failure guarantee, and that failed calls spend nothing. It also discloses the async contract (an id is returned immediately, poll get_video about once a minute until ready or failed), which no annotation conveys. The new-video-beside-it wording usefully clarifies that destructiveHint=true refers to spending credits, not to overwriting the source video.

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?

Cost and the eligibility gate are front-loaded, and each sentence carries information. Some phrasing is convoluted ("made again into a new video beside it, as the app's Change does"), which costs a bit of clarity.

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

Completeness5/5

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

For a paid, asynchronous mutation with no output schema, the description covers everything an agent needs: eligibility gate, cost, refund behavior, immediate return value, and the polling loop. Nothing essential is missing.

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 coverage is 100%, so every parameter already carries its own description, and the description mostly restates that credits is the after_steps figure and change is the person's own words. It adds no format, length, or validation detail beyond the schema, so the baseline 3 applies.

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?

States a specific verb and resource (change one finished video) and immediately clarifies the output shape: a new video created beside the original rather than an in-place edit. That distinction separates it from make_video, make_longer, and other_sizes without needing their schemas.

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?

Gives a hard precondition ("Only for a video whose after_steps offers it") and explains the rejection path for impossible changes, which tells the agent when not to retry. It stops short of naming sibling alternatives such as make_longer or other_sizes that might apply instead, so a 4 rather than a 5.

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

All Say It Again tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.