Skip to main content
Glama

Start an AI character swap

start_swap

Swaps one of your characters into a ready source video (or a reel link). Uses AI swap credits from your plan or a swap pack. Sharing plans and the Free plan include none: then the answer is code plan_limit with an upgrade_url to show the user. Returns the video id; poll get_video until ready (about 8 minutes). start/end: seconds of the source to swap (default: from the start, up to your plan limit).

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": {
      "character_id": "<character_id>"
    },
    "name": "start_swap"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
startNo
promptNoExtra direction for the swap
subjectNoWho to replace, e.g. "the woman in red" (default: the main person)
source_idNoA ready source from get_upload
source_urlNoOr a reel link (the worker downloads it)
character_idYes

Output Schema

NameRequiredDescriptionDefault
app_urlYes
video_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations (non-read-only, non-idempotent, open-world), the description discloses that the call consumes AI swap credits, that Free/Sharing plans have none, that failure returns code plan_limit plus an upgrade_url to surface to the user, and that the operation is asynchronous with ~8 minutes to completion. That is substantial behavior an agent could not infer from structured fields alone.

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?

Front-loaded with the action and credit cost, then error handling, then async follow-up, then parameter semantics — a sensible order with little waste. The telegraphic 'start/end:' shorthand and the slightly awkward 'include none' phrasing keep it from being polished, but no sentence is redundant.

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?

For a 7-param, 1-required mutation with an output schema, it covers cost, failure mode, async lifecycle, and duration limits. The one gap is that it never clarifies choosing source_id vs source_url (they appear mutually exclusive), leaving that to the schema descriptions.

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 57%, so the description must carry some weight, and it does: it explains that start/end are seconds of the source to swap, default to the start, and are capped by the plan limit — none of which is in the schema. It adds nothing about prompt, subject, or the source_id/source_url exclusivity, which the schema mostly covers already.

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: swapping one of your characters into a ready source video or reel link. It also implicitly distinguishes itself from upload/commit siblings by requiring a 'ready source from get_upload' and from get_video by naming it as the polling follow-up.

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?

Clear on when to use it (swap a character into a ready source) and what to do afterwards (poll get_video until ready, ~8 minutes). It also prescribes handling of the plan_limit error. It does not explicitly exclude alternate paths such as use_own_video or add_video_link, so it stops short of full when-not guidance.

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.