Skip to main content
Glama
Sign In

Ignix

by social.ignix
OverviewDiscussionsAdmin

Run Autopilot (create a content plan as drafts)

run_autopilot

Run Ignix Autopilot — the same as the Autopilot panel in the calendar. It plans a run of content from what is working in the brand’s niche right now and on its own account (each piece with a goal and a format), writes every piece in each account’s voice (on X it leans on what is working in the niche on X), makes the images and leaves everything as DRAFTS with suggested dates for the user to review. Reels can be "reel_claude" (made later by you with get_reel_playbook; they show up in list_pending_reels). It runs in the background: drafts appear in the calendar within a few minutes and the user gets an email. Nothing is published. Costs AI credits: 25 once for the plan (when it plans several ideas, a period or has no topic), 35 per piece PER ACCOUNT (3 ideas on 2 accounts = 6 pieces), and 20 per image (40 when it carries the speaker's photos or character; a carousel has 3 by default). If the credits do not cover the run it is not started and you get what it needs and what is left. Tell the user what you are about to run (accounts, period, number of ideas) before calling it. To discuss the plan first without creating anything, use plan_campaign; for one piece, plan_content. SPENDS AI CREDITS ONLY WITH confirm: true. Call it first without confirm: nothing runs and nothing is charged, you get the quote (what it will do and the credits). Tell the user, in your own words, exactly that — including the options you chose, so they can change them — and wait for a clear yes before calling again with the same arguments and confirm: true. One yes covers the plan they approved (e.g. every line of an approved voice-over with the chosen voice); anything new or different needs a new yes.

Input Schema

NameRequiredDescriptionDefault
whenNoWhen the pieces go: today, tomorrow, this_week, next_week, this_month or next_month. Default today.
countNoHow many ideas (1-20). Each one becomes a piece per account. For a week, 3-5 is typical.
topicNoOptional brief: a launch, a theme, a date. Leave it out to let the plan come from what is working in the brand’s niche and on its own account — usually the better choice.
formatNoForce a format, or "auto" (default) to let the plan choose per piece. "reel_claude" = reels you make later on your computer with Ignix Editor, as get_reel_playbook says. "video_claude" = long horizontal YouTube videos you make later the same way (only on YouTube accounts; elsewhere it becomes a reel).
confirmNotrue ONLY after the user said yes to the quote (what it does and the credits). Without it nothing runs and nothing is charged.
accountIdsYesAccount ids from list_accounts (the ones to plan for).
keywordCtaNoAllow a "comment WORD" call to action with its comment-to-DM automation, only for resources the brand has on file. Default false.
withImagesNoGenerate an image for each post (default true).
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.
idempotencyKeyNoOptional. A unique id for this action (16-128 chars: letters, digits, _ : . -). If you are unsure whether a call went through (timeout, network error), repeat it with the SAME idempotencyKey and the same arguments: you get the original result and nothing is done twice.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint false, destructiveHint false, openWorldHint true), the description discloses that the run happens in the background, drafts appear within a few minutes, an email is sent, and nothing is published. It also details AI credit pricing (25 for the plan, 35 per piece per account, 20 per image), what happens if credits are insufficient, and how the confirm flag gates spending.

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 description is long but front-loads the core purpose before moving into costs, the confirmation workflow, and alternatives. It is appropriately detailed for a costly, multi-step operation, though some repetition around 'nothing is published' and the confirmation steps could be tightened.

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?

Given the tool's complexity (ten parameters, background execution, credit spending, and no output schema), the description covers everything an agent needs: what it produces, where results appear, how long it takes, credit implications, the confirmation requirement, and alternatives. No critical behavioral or contextual gap remains.

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 description coverage is 100%, so the schema already explains all ten parameters, establishing a baseline of 3. The description adds useful semantics beyond the schema, such as the credit cost model tied to count, accounts, and images, and the behavior of format values like 'reel_claude' and 'video_claude' (e.g., video_claude becomes a reel outside YouTube).

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?

The description states a specific verb and resource: plans a run of content as drafts, writes pieces in each account's voice, makes images, and leaves everything as drafts. It explicitly distinguishes itself from sibling tools by naming plan_campaign and plan_content as alternatives for discussing or single-piece planning.

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?

It gives explicit when-to-use guidance, including alternatives: use plan_campaign to discuss the plan first, plan_content for one piece. It also spells out the two-step confirmation workflow, stating that a first call without confirm returns a quote and nothing is charged, and that a clear yes is required before the real run.

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