Skip to main content
Glama

kelpo_create_music_clip

Create a music clip (a rap/song music video of the account's actors; no LLM on Kelpo's side: you write everything). Flow: 1) this call with the lyrics as sections (each sung section has ONE singer = a cast person_id; write the lines as they must be PRONOUNCED, e.g. a brand « Le Crew » said « le crou » → « Le Crou »; about 4 short lines per 10 s of rap; an intro and a break without lines become dance shots), an English music style, the cast (library people with photos, each with an English look and a clearly different English voice) and the end card (logo image already uploaded, text such as the website; the music ends under it). 2) kelpo_generate_music: price, then confirmed=true; when the music is ready (kelpo_get_music_clip), give its link to the user. 3) kelpo_plan_music_clip_shots: an English set, action and camera for EVERY segment listed. 4) kelpo_render_music_clip: quote, then confirmed=true with max_credits. The final clip is a video of the project (kelpo_get_job / kelpo_videos). No subtitles are burnt in. Arguments: {"body": {"title": "", "style": "", "cast": [], "sections": []}}

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": {
      "body": "<body>"
    },
    "name": "kelpo_create_music_clip"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false, idempotentHint=false). The description adds real behavioral context beyond them: the orchestration is non-idempotent (a separate price+confirmed step gates spending credits), the client AI authors all content because there is no LLM on Kelpo's side, and 'no subtitles are burnt in' sets an output expectation. It stops short of saying what this specific call returns (project id? music clip id?) or whether it itself consumes credits.

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?

Purpose is front-loaded in the first clause, then the numbered flow gives a scannable sequence. It is dense and parenthesis-heavy, and roughly half the text describes sibling tools' steps rather than this call's own arguments, but each of those steps is load-bearing guidance and no sentence is pure filler.

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 deeply nested, multi-stage tool with no output schema, the description covers input authorship rules, ordering, cost gates and the final artifact. The notable gap is the return value of this particular call, which an agent needs in order to chain to kelpo_generate_music; it implies the flow but never names what id comes back.

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?

Top-level schema coverage is effectively 0% (one 'body' param), so the description has to carry the weight and largely does: it explains sections/lyrics (pronounce as spoken, e.g. 'Le Crew' → 'Le Crou', ~4 short lines per 10 s, one singer per sung section by person_id), instrumental sections becoming dance shots, the English style string, the cast needing distinct English voices, and the end card ending over the music. It omits bpm, key, seed, seconds, language and client_id entirely, which the nested schema documents but the description does not reinforce.

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+resource ('Create a music clip') and immediately qualifies it ('a rap/song music video of the account's actors; no LLM on Kelpo's side: you write everything'), which distinguishes it from the sibling kelpo_generate_music (which actually renders the audio) and from kelpo_create_project/kelpo_generate. An agent can tell what this call produces without opening the schema.

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 workflow: this call first, then kelpo_generate_music with a price and confirmed=true, then kelpo_get_music_clip, then kelpo_plan_music_clip_shots, then kelpo_render_music_clip with quote and max_credits. It also states prerequisites and hand-offs (logo must already be uploaded, cast members come from the people library) and the post-condition (result retrieved via kelpo_get_job / kelpo_videos).

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