Skip to main content
Glama
Sign In

Ignix

by social.ignix
OverviewDiscussionsAdmin

Analyse a public account (competitor or reference)

research_account

What is working for a PUBLIC Instagram, TikTok or YouTube account or Facebook PAGE: its profile and its latest reels or Shorts with views, likes and comments, the account's median views and which pieces stand out (2× the median or more). When an Instagram account posts mostly photos and carousels (Instagram only gives views for videos), pieces are compared by likes + comments instead (see the "metric" field). Use it to see what a competitor or a reference creator does well and which formats to model — never to copy their words. The first analysis of an organization is free; then 10 AI credits for Instagram, 120 for TikTok or YouTube and 30 for a Facebook page — its latest posts with reactions, comments, shares and video views, compared by interactions (12 pieces; a deeper Instagram look, up to 30 reels, costs 85 per 12). Tell the user the cost first. For a whole topic use research_niche; for a single piece, analyze_reel; to reread an earlier analysis without running it again, get_research. 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
depthNoHow many recent pieces (default 12, max 30). More only if the user asks for a deep look.
handleYesThe account, e.g. "canva" or "@canva" or its profile URL. Facebook: the page name or its URL (facebook.com/name or facebook.com/profile.php?id=…); personal profiles cannot be analysed.
confirmNotrue ONLY after the user said yes to the quote (what it does and the credits). Without it nothing runs and nothing is charged.
networkYes
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. Changed2 schema fields changed
    • changedInput schema / properties / handle / description
      Previous value: -"The account, e.g. \"canva\" or \"@canva\" or its profile URL."New value: +"The account, e.g. \"canva\" or \"@canva\" or its profile URL. Facebook: the page name or its URL (facebook.com/name or facebook.com/profile.php?id=…); personal profiles cannot be analysed."
    • changedInput schema / properties / network / enum
      Previous value: -[
-  "instagram",
-  "tiktok",
-  "youtube"
-]New value: +[
+  "instagram",
+  "tiktok",
+  "youtube",
+  "facebook"
+]
  2. First observed

TDQS

A4.7/5.0
Behavior5/5

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

Annotations only declare readOnlyHint=false, destructiveHint=false, openWorldHint=true. The description goes far beyond: per-network credit costs, the free first analysis of an organization, the deeper Instagram option cost, the quote-without-confirm mode that runs nothing and charges nothing, and the scope of a single user 'yes'. These are exactly the behavioral traits an agent needs before invoking a credit-spending tool.

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 and sibling routing are front-loaded and efficient, but the cost passage is a long run-on with an embedded parenthetical ('120 for TikTok or YouTube and 30 for a Facebook page — its latest posts with reactions...') that is hard to parse, and the confirm workflow is restated at length. The content earns its place; the packing does not.

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?

With no output schema, the description still tells the agent what comes back (profile plus recent pieces with views/likes/comments, median views, standout pieces, the metric field switching to likes+comments for photo-heavy Instagram accounts). Combined with cost, confirm flow, and limits, an agent has everything needed to call it correctly.

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 high (83%), so the baseline is 3, but the description adds real meaning: it explains the depth tradeoff (12 default, up to 30 deeper, costs 85 per 12 on Instagram), the public-only constraint for handles and Facebook pages vs personal profiles, and the semantics of confirm beyond the schema's phrasing (nothing runs and nothing is charged without it). It does not elaborate workspaceId, leaving that 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?

The description opens with a specific verb+resource: analysing a PUBLIC Instagram, TikTok, YouTube account or Facebook PAGE, enumerating exactly what it returns (latest reels/Shorts with views/likes/comments, median views, standout pieces at 2x median). It names and routes away from the three closest siblings (research_niche, analyze_reel, get_research), so an agent can disambiguate 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 Guidelines5/5

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

It states the intended use (see what a competitor or reference creator does well, model formats, never copy words) and explicitly points to alternatives for adjacent tasks: whole topic -> research_niche, single piece -> analyze_reel, reread earlier analysis -> get_research. The confirm-first workflow (call without confirm to get a quote, then call again with confirm:true after a clear yes) is spelled out as an operational rule.

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