Skip to main content
Glama
Sign In

Ignix

by social.ignix
OverviewDiscussionsAdmin

How to make a reel (rendered on the user's computer + Ignix voice)

get_reel_playbook
Read-onlyIdempotent

Call this ONLY when the user wants a video made: a reel or Short (default), or a long horizontal YouTube video (length "long"). Returns the step-by-step playbook to build it on the user's machine with Ignix Editor (installed if missing), the craft rules for hooks and pacing, hook patterns from the Ignix library for this brand, and the voices available for the voice-over. With pieceId (a reel Autopilot planned, see list_pending_reels) it also returns that piece's brief and the draft the video must be attached to. With reference (a reel the user wants this one to look like) it adds the steps to break that reel down and rebuild its format. Call it even from a chat that cannot run commands: the playbook still plans the video and says how the render is handed off. Reels need no AI video provider. It returns the CORE (steps, approvals, minimums) and the list of sections; call it again with section when you reach each step.

Input Schema

NameRequiredDescriptionDefault
topicNoWhat the reel is about, if the user said it.
lengthNo"short" (default): a vertical reel / Short. "long": a horizontal video of several minutes for YouTube (tutorial, explainer, story, history, list, documentary…), with its own playbook.
pieceIdNoId of a reel Autopilot planned (from the user's email or list_pending_reels). Brings its brief and its draft.
sectionNoOne section of the playbook, named in the core (call without it first). Pass the same pieceId or length.
languageNoLanguage of the reel, e.g. es or en. Defaults to the brand's.
platformNoNetwork it is for: instagram (default), tiktok, youtube, facebook…
referenceNoA reel or video the user wants this one to look like ("make one like this"): its URL (Instagram, TikTok, YouTube) or the path of the file on their machine. Adds the steps to break it down and rebuild its format for this brand.
workspaceIdNoWorkspace to work on (an id from list_workspaces). Not needed when this connection is tied to one workspace, or when you pass an account: the account's workspace is used.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / section
      Added value: +{
+  "description": "One section of the playbook, named in the core (call without it first). Pass the same pieceId or length.",
+  "enum": [
+    "setup",
+    "brand",
+    "research",
+    "script",
+    "sound",
+    "direction",
+    "render",
+    "thumbnail",
+    "reference",
+    "approved_script"
+  ],
+  "type": "string"
+}
  2. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag readOnly/idempotent/non-destructive, and the description adds real behavioral context beyond them: it explains the core-plus-sections protocol ('call it again with `section` when you reach each step'), that it works from chats that cannot run commands, and that reels need no AI video provider. This is a strong disclosure of how the tool behaves over multiple calls.

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?

The intent is front-loaded in the first sentence and each sentence carries real content. However, it is a dense single paragraph mixing purpose, return contents, and multi-call protocol; breaking the section protocol into a separate clause would improve scanability.

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?

There is no output schema, so the description must explain returns, which it does well (core, sections, briefs, drafts). It could be slightly clearer about what 'CORE' contains, but for a read-only planning tool it is largely complete.

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, but the description goes further: it explains that pieceId pulls a brief and draft, that reference adds breakdown/rebuild steps, and that `section` must be passed with the same pieceId or length. This adds usage semantics the schema alone doesn't convey.

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?

Names a specific verb+resource and scopes it tightly: 'Call this ONLY when the user wants a video made: a reel or Short (default), or a long horizontal YouTube video.' It also distinguishes itself from neighboring planning tools by describing exactly what it returns (playbook, craft rules, hook patterns, voices). An agent can tell it apart from get_edit_playbook or plan_video_edit without opening a schema.

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?

Strong when-to-use with an explicit ONLY condition, plus routing hints ('with pieceId ... see list_pending_reels'). It does not explicitly name the alternative for editing an existing video (get_edit_playbook), so a sibling edge case is left to inference, but the core usage rule is clear.

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

All Ignix toolsInspect
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.

Resources