Skip to main content
Glama

kelpo_swap_person

Replace one or two people of an uploaded video by actors (no LLM). Flow: upload the video to the conversation with a reference upload of role swap_source (4 to 15 s, 95 MB, MP4/MOV/WebM; its swap block lists the people found, the price and the delivery time); call this with confirmed=false (dry run) → price in credits, people (index, position from left to right) and what is missing; ask the user who to replace when several people are found (one or two people; each = index, or point when not found) and which actor replaces each (catalogue, library person, or 1-5 photos; 3 photos per actor when two are replaced, photo_indexes / photo_ids = the ones chosen when an actor has more): targets = [{person, actor}, …] (one person: person/point/actor also work); then confirmed=true with max_credits = the approved price (and rights_confirmed=true only after the user declared their rights on the video/photos and the agreement of the people shown). The result is a 2K video of the same length, made in ONE shot (no seams), with the original sound; price 20 credits per second, the same for one or two people; follow it with kelpo_get_job (≈ 15 min for 10 s; estimated_minutes in the dry run). Clothes, place, camera and movements come from the video; only the chosen people change. Arguments: {"path": {"id": ""}, "body": {"source_asset_id": "<source_asset_id>"}}

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": {
      "path": "<path>",
      "body": "<body>"
    },
    "name": "kelpo_swap_person"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes
pathYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior3/5

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

Annotations declare this is a non-read-only, non-destructive, non-idempotent operation, and the description goes well beyond that with pricing (20 credits/second, same for one or two people), a ~15 min estimate for a 10 s clip, the max_credits guard that refuses if the price changed, and the rights_confirmed gate. It also discloses output traits (2K, same length, one shot with no seams, original sound preserved) and that only the chosen people change while clothes/place/camera/movement come from the source. It does not explain idempotency_key behaviour or failure/refund handling, so with annotations already covering the safety profile this is strong but not exhaustive.

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

Conciseness3/5

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

The purpose is front-loaded, but the body is a single dense run-on held together by semicolons and nested parentheses, which makes the critical dry-run-then-confirm sequence harder to scan than it needs to be. Most sentences carry real information, so the issue is structure rather than padding.

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 nested two-person swap tool with a paid, irreversible render, the description covers the prerequisite upload, the two-phase call, actor sourcing options, pricing and time, consent requirements, and the follow-up job tool. There is no output schema, and the description still describes the returned artifact sufficiently.

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?

Adds real meaning beyond the schema: it explains the dry-run vs confirmed semantics, that max_credits is the approved price, the targets = [{person, actor}] shape with person/point/actor as the single-person alternative, that person is the index from left to right among `people`, and when photo_indexes/photo_ids apply. It leaves idempotency_key and the optional `scene` hint unexplained, so it is not fully complete.

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?

Opens with a specific verb and resource: 'Replace one or two people of an uploaded video by actors (no LLM)'. The '(no LLM)' note and the video-in/video-out framing separate it cleanly from siblings like kelpo_generate or kelpo_actor_catalog, which are referenced only as supporting steps.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Gives an explicit ordered flow: upload with role swap_source, call with confirmed=false as a dry run, ask the user which people to replace and with which actor, then confirmed=true with max_credits, then poll kelpo_get_job. Preconditions (rights_confirmed only after the user declares rights and consent) and alternatives for actor sourcing (catalogue, library, 1-5 photos) are spelled out.

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