ShortsIntel

Add to a collection

add_to_collection

Use when putting a Tracker into a Collection (id or name): by tracker_id, or by platform + target, which starts a Tracker if not tracked yet. Not for a focus or a refresh: track (its collection argument files it too). Price: Free for a Tracker you have; a new target runs its first cycle: creator 6, hashtag 3, keyword 3, sound 6, advertiser 30 credits; +20 credits per new video analysed. A new name creates the Collection with the Tracker's kind (pass kind with a target); another kind is collection_kind_mismatch. Collections mix Meta, Google and TikTok Advertisers.

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": {
      "collection": "<collection>"
    },
    "name": "add_to_collection"
  }
}

Input Schema

Name	Required	Description
`kind`	No	Adding by target: the Tracker's kind. Required for a new Collection.
`target`	No	Handle, hashtag, phrase (kind=keyword), sound id, Page id, or with platform tiktok or platform google an advertiser id, URL or name
`estimate`	No	Quote the price in Credits: no Run, no charge
`platform`	No	With target, instead of tracker_id
`collection`	Yes	The Collection, by id or name. A new name creates it, with the Tracker's kind.
`tracker_id`	No	A Tracker you already have
`max_credits`	No
`intelligence`	No	Analyse new videos, when the target is not tracked yet

Output Schema

Name	Required	Description
`run`	No	The new Tracker's first cycle; null when nothing was created.
`added`	No	False when the Tracker was already a member (200), or, with `collection_error`, when the Collection was deleted before the new Tracker could join (201).
`cached`	No
`created`	No	True when this call started tracking the target.
`tracker`	No	The member, as it now is, state included.
`per_cycle`	No
`collection`	No	Absent only with `collection_error`.
`tracker_id`	No
`already_tracking`	No
`collection_error`	No	Only when the Collection was deleted while the new Tracker's first cycle ran.
`estimate_credits`	No
`intelligence_run`	No	The Run analysing the first cycle's new Ads (an advertiser Tracker with `intelligence.

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 8, 2026

changedInput schema / properties / platform / enum

Previous value: -[
-  "tiktok",
-  "instagram",
-  "youtube",
-  "facebook"
-]New value: +[
+  "tiktok",
+  "instagram",
+  "youtube",
+  "facebook",
+  "meta",
+  "google"
+]

changedInput schema / properties / target / description

Previous value: -"Handle, hashtag, search phrase (kind=keyword), sound id, Page id, or with platform tiktok a TikTok ad library advertiser id, URL or name"New value: +"Handle, hashtag, phrase (kind=keyword), sound id, Page id, or with platform tiktok or platform google an advertiser id, URL or name"

Changed2 schema fields changedNov 8, 2026

changedInput schema / properties / collection / description

Previous value: -"The Collection, by id or name. A name you have not used yet creates it, with the Tracker's kind."New value: +"The Collection, by id or name. A new name creates it, with the Tracker's kind."

changedInput schema / properties / kind / description

Previous value: -"Adding by target: the Tracker's kind. Required when the Collection does not exist yet."New value: +"Adding by target: the Tracker's kind. Required for a new Collection."

Changed3 schema fields changedNov 5, 2026
- changedInput schema / properties / estimate / description
```
Previous value: -"Return the price, in Credits, without running the operation or creating a Run"New value: +"Quote the price in Credits: no Run, no charge"
```
- changedOutput schema / properties / collection / additionalProperties
```
Previous value: -trueNew value: +{}
```
- removedOutput schema / properties / collection / properties
```
Removed value: -{}
```
Changed1 schema field changedNov 4, 2026
- addedInput schema / properties / max_credits
```
Added value: +{
+  "minimum": 0,
+  "type": "integer"
+}
```

Changed1 schema field changedNov 4, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "added": {
+      "description": "False when the Tracker was already a member (200), or, with `collection_error`, when the Collection was deleted before the new Tracker could join (201).",
+      "type": "boolean"
+    },
+    "already_tracking": {
+      "type": "boolean"
+    },
+    "cached": {
+      "type": "boolean"
+    },
+    "collection": {
+      "additionalProperties": true,
+      "description": "Absent only with `collection_error`.",
+      "properties": {},
+      "type": "object"
+    },
+    "collection_error": {
+      "$ref": "#/properties/collection",
+      "description": "Only when the Collection was deleted while the new Tracker's first cycle ran."
+    },
+    "created": {
+      "description": "True when this call started tracking the target.",
+      "type": "boolean"
+    },
+    "estimate_credits": {
+      "type": "integer"
+    },
+    "intelligence_run": {
+      "anyOf": [
+        {
+          "$ref": "#/properties/collection"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The Run analysing the first cycle's new Ads (an advertiser Tracker with `intelligence."
+    },
+    "per_cycle": {
+      "type": "boolean"
+    },
+    "run": {
+      "anyOf": [
+        {
+          "$ref": "#/properties/collection"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "description": "The new Tracker's first cycle; null when nothing was created."
+    },
+    "tracker": {
+      "$ref": "#/properties/collection",
+      "description": "The member, as it now is, state included."
+    },
+    "tracker_id": {}
+  },
+  "type": "object"
+}

First observedNov 2, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare a non-readonly, non-idempotent, open-world mutation, and the description adds substantial context beyond them: a side effect (a Tracker is started for an untracked target), per-kind credit costs plus a per-video surcharge, and a named error outcome (collection_kind_mismatch). The only missing piece is what max_credits does when the quote exceeds it.

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?

Front-loaded with the correct routing sentence and free of filler, but the pricing block is written in dense shorthand ('creator 6, hashtag 3, keyword 3, sound 6, advertiser 30 credits; +20 credits per new video analysed') that reads more like a table dump than prose. It is appropriately sized for an 8-parameter cost-incurring mutation, yet the telegraphic style costs some readability.

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?

For a mutating, credit-charging tool, the description covers side effects, cost, error paths, and collection-creation semantics, and an output schema exists so return values need not be explained. Nothing essential for a correct call is missing apart from the minor max_credits gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 88%, so the baseline is 3, and the description earns a bit more by stating the cross-field constraint that kind must accompany target for a new Collection and that platform + target replaces tracker_id. However max_credits remains undocumented in both schema and description, and estimate/max_credits interactions with the price paragraph are left implicit.

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?

States a specific verb and resource ('putting a Tracker into a Collection') and immediately enumerates the two supported addressing modes (tracker_id, or platform + target). It is clearly distinguishable from siblings such as create_collection, act_on_collection, and track, which are named.

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?

Explicitly gives a when-not rule ('Not for a focus or a refresh') and routes the agent to the correct alternative ('track (its collection argument files it too)'). It also covers the create-on-the-fly case, which is the main ambiguity an agent would face.

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

All ShortsIntel 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.

Resources

Need Help?