ShortsIntel

Get change reports

get_changes

Read-onlyIdempotent

Use when you need what changed for a Tracker, or a Collection merged newest first: new videos, outliers, follower and view moves, velocity spikes, new top videos, new or stopped Ads, with before/after. Not for a Tracker's current state or sample: get_tracker. For fresh numbers now: track with refresh=true (charged). Price: Free. Pass tracker_id or collection (id or name), not both; since keeps later reports. New Ads carry analysis and analysis_status. With a focus, only in-focus videos are listed and off_focus_count counts the rest; include_off_focus=true lists them with verdicts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_changes"
  }
}

Input Schema

Name	Required	Description
`limit`	No
`since`	No	Reports written after this ISO 8601 time.
`cursor`	No
`collection`	No	Or a Collection, by id or name: every member's reports in one feed.
`tracker_id`	No	One Tracker's reports.
`include_off_focus`	No	true: a report with a focus also lists the off-focus videos it hid (off_focus_videos), each with its verdict and reason.

Output Schema

Name	Required	Description	Default
`items`	No
`next_cursor`	No	Pass back as `cursor`.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 8, 2026

changedInput schema / properties / since / description

Previous value: -"collection only: reports written after this ISO 8601 time."New value: +"Reports written after this ISO 8601 time."

Changed5 schema fields changedNov 5, 2026

removedOutput schema / properties / items / anyOf

Removed value: -[
-  {
-    "items": {
-      "additionalProperties": true,
-      "properties": {},
-      "type": "object"
-    },
-    "type": "array"
-  },
-  {
-    "items": {
-      "$ref": "#/properties/items/anyOf/0/items"
-    },
-    "type": "array"
-  }
-]

addedOutput schema / properties / items / items

Added value: +{
+  "additionalProperties": {},
+  "type": "object"
+}

addedOutput schema / properties / items / type
```
Added value: +"array"
```

removedOutput schema / properties / next_cursor / anyOf

Removed value: -[
-  {
-    "type": [
-      "string",
-      "null"
-    ]
-  },
-  {
-    "type": [
-      "string",
-      "null"
-    ]
-  }
-]

addedOutput schema / properties / next_cursor / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed1 schema field changedNov 4, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": true,
+  "properties": {
+    "items": {
+      "anyOf": [
+        {
+          "items": {
+            "additionalProperties": true,
+            "properties": {},
+            "type": "object"
+          },
+          "type": "array"
+        },
+        {
+          "items": {
+            "$ref": "#/properties/items/anyOf/0/items"
+          },
+          "type": "array"
+        }
+      ]
+    },
+    "next_cursor": {
+      "anyOf": [
+        {
+          "type": [
+            "string",
+            "null"
+          ]
+        },
+        {
+          "type": [
+            "string",
+            "null"
+          ]
+        }
+      ],
+      "description": "Pass back as `cursor`."
+    }
+  },
+  "type": "object"
+}

First observedNov 2, 2026

TDQS

A4.6/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, so the safety profile is covered; the description adds genuinely new behavior: 'Price: Free', newest-first merge order for collections, that 'since keeps later reports', and that focus-filtered reports hide off-focus videos unless include_off_focus=true. It stops short of describing pagination behavior or result volume, which keeps it off a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the trigger, then exclusions, then price, then parameter constraints, then edge-case behavior — a clear priority order. It is dense but every sentence adds a fact an agent would otherwise get wrong; there are no filler sentences.

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 read-only feed tool with an output schema (so return shape needn't be explained), the description covers routing, pricing, ordering, mutual exclusivity, and focus semantics. The remaining gap is pagination — how to use cursor and what limit does — which matters for a report feed that could be long.

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?

With 67% schema coverage, the description still contributes real semantics the schema lacks: the mutual exclusivity rule ('Pass tracker_id or collection (id or name), not both'), collection name-or-id acceptance, and the include_off_focus side effect (verdicts and off_focus_count). It says nothing about limit (max 100) or cursor paging, so two parameters remain effectively undocumented.

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 uses a specific verb+resource ('what changed for a Tracker, or a Collection') and enumerates the report kinds (new videos, outliers, follower/view moves, velocity spikes, ads) so an agent knows exactly what comes back. It explicitly distinguishes itself from get_tracker and track, which is the key sibling ambiguity.

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 a positive trigger ('Use when you need what changed'), two explicit exclusions with named alternatives ('Not for a Tracker's current state or sample: get_tracker', 'For fresh numbers now: track with refresh=true (charged)'), and flags the cost of the alternative. Nothing about routing is left to inference.

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?