Marsell

Make a series

series_create

Makes a series for the project, as a draft: nothing is made, spent or posted until series_start. Marsell can run a series in the owner's own voice, made and posted every day from the day's news on a topic (for example daily archaeology news): each day it searches the news on the topic, drops what the series already reported, picks the best new story and makes a cited Short about it, narrated in a voice the project kept (the owner's own clone: voice_clone); a day with no new story gets no episode. For that, give kind video, a topic (what the news is about: "archaeology: new finds, digs and research"), cadence daily, and narrator_voice: the voiceId of a voice the project kept (voices_read lists them; voice_clone makes the owner's own). Without a topic Marsell plans the series a season at a time in Marsell. A video series starts with two video types, a Short and a long film; each is the owner's to shape after it is made with series_video_type_set (motion graphics in code, AI video, stills or a mix; any length from 5 seconds; the shape in the owner's words; narrated or no voice; music; how many a week), which says what an episode then costs. Before creating or starting one, quote the month with series_quote and tell the owner the tokens each episode and the month may use, whether their plan holds it, and what it costs them in dollars a month (costs_the_owner: the price of the plan that holds it). Free.

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": {
      "name": "<name>"
    },
    "name": "series_create"
  }
}

Input Schema

Name	Required	Description
`kind`	No	video (the default), pictures or newsletter. A series from the news is a video series.
`name`	Yes	The series' name: "Ancient Finds Daily".
`time`	No	The time it comes out, HH:MM (18:00 when left out).
`about`	No	What it is about and who it is for, in the owner's words.
`notes`	No	With a topic: what the owner wants from the stories (what to lean on, what to leave out).
`topic`	No	Makes it a series from the day's news on this topic.
`format`	No	A video series' video type: original-short (the default) or original-long.
`cadence`	No	How often it comes out. Or per_week.
`project`	No	The project's id or exact name. Optional when the account has one project.
`per_week`	No	Episodes a week, 0 to 21 (7 is every day). Instead of cadence.
`timezone`	No	The owner's time zone, IANA: "Europe/Berlin" (UTC when left out).
`narrator_voice`	No	A video series' narrator: the voiceId of one of the project's kept voices (voices_read).

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare this is a non-destructive, closed-world write; the description adds far more - the object is a draft with no spend or posting until series_start, the tool is free at creation, and cost only materializes per episode after series_video_type_set. It also discloses runtime behavior of a topic series (daily news search, dedupe against prior episodes, skipped days when no new story) which no annotation covers.

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 most important facts (draft, no spend, quote first) are front-loaded, but the body is a single sprawling run-on dense with nested parentheses, and the cost/quotation guidance appears twice in different framings. It is information-rich yet harder to parse than it needs to be.

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 12-parameter creation tool with no output schema, the description supplies the lifecycle (draft -> video type -> quote -> start), the cost implication, and the sibling tools needed at each step. The remaining gap is that it never says what a successful call returns (a series id, presumably needed for series_start), which matters more given there is no output schema.

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 100%, so the baseline is 3; the description earns above that by tying parameters into a concrete recipe - 'give kind video, a topic ..., cadence daily, and narrator_voice: the voiceId of a voice the project kept' - and by cross-referencing voices_read/voice_clone for narrator_voice. It does not, however, explain format, time, timezone, per_week or notes, leaving those to the schema.

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?

Opening clause delivers a specific verb and resource ('Makes a series for the project, as a draft') and immediately delineates the boundary from series_start ('nothing is made, spent or posted until series_start'). The subsequent explanation of the news-to-episode pipeline makes clear this is a planning/creation tool, not a publishing one.

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?

Explicit routing is provided: quote the month with series_quote before creating or starting, shape video types afterward with series_video_type_set, and consult voices_read/voice_clone for narrator_voice. It also states the branch condition for omitting topic ('Without a topic Marsell plans the series a season at a time'). That is when-to-use, when-not, and alternatives in one pass.

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

All Marsell 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.