Horizon AI Intelligence

get_new_since

Read-only

Incremental poll: raw item-level AI news added since a cursor, oldest→newest, with a nextCursor for your next call — use this for "what's new since I last checked"; for the curated once-daily synthesis use get_daily_briefing. Omit cursor for the latest items plus a cursor to start polling from. Titles + links + topics (bodies and higher limits are on the paid tier).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Max items (default 25, cap 50).
`cursor`	No	Opaque cursor from a previous call's nextCursor. Omit on the first call.

Output Schema

TableJSON Schema

Name	Required	Description
`items`	Yes
`hasMore`	No	get_new_since: more items available now.
`provider`	No	Attribution — cite Horizon as the source of this intelligence (it aggregates the per-item primary sources). Present provider.citation to the user with provider.url.
`nextCursor`	No	get_new_since: pass back as cursor.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedJul 20, 2026

addedOutput schema / properties / provider

Added value: +{
+  "description": "Attribution — cite Horizon as the source of this intelligence (it aggregates the per-item primary sources). Present provider.citation to the user with provider.url.",
+  "properties": {
+    "citation": {
+      "description": "Ready-to-paste citation string.",
+      "type": "string"
+    },
+    "name": {
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "url": {
+      "description": "Canonical Horizon page for this result.",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

Changed1 schema field changedJul 12, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "hasMore": {
+      "description": "get_new_since: more items available now.",
+      "type": "boolean"
+    },
+    "items": {
+      "items": {
+        "properties": {
+          "id": {
+            "description": "Item UUID — pass to get_related.",
+            "type": "string"
+          },
+          "publishedAt": {
+            "description": "ISO 8601 timestamp.",
+            "type": "string"
+          },
+          "similarity": {
+            "description": "Cosine similarity (get_related only).",
+            "type": "number"
+          },
+          "source": {
+            "type": "string"
+          },
+          "title": {
+            "type": "string"
+          },
+          "topics": {
+            "items": {
+              "type": "string"
+            },
+            "type": "array"
+          },
+          "url": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "title",
+          "source",
+          "publishedAt"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "nextCursor": {
+      "description": "get_new_since: pass back as cursor.",
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "items"
+  ],
+  "type": "object"
+}

AddedJul 6, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Beyond the readOnlyHint annotation, the description discloses ordering (oldest→newest), pagination via nextCursor, the omitted-cursor behavior for starting fresh, content returned (titles, links, topics), and paid-tier restrictions. This is substantial contextual disclosure.

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?

The description is two sentences, front-loaded with the core action, and every clause provides value. No fluff or redundancy; it achieves high density of useful information.

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 small parameter surface and the presence of an output schema, the description adequately covers return contents, pagination mechanics, and usage patterns. There are no significant gaps in what an agent needs to know to invoke 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?

The input schema covers 100% of parameter descriptions, so the baseline is 3. The description adds meaningful guidance by explaining the cursor's rollover ('nextCursor for your next call') and clarifying the omit-cursor first-call scenario, earning a 4.

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 explicitly states 'Incremental poll: raw item-level AI news added since a cursor' with a clear verb and resource, and distinguishes itself from get_daily_briefing. It is specific and unambiguous.

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 provides an explicit use case ('what's new since I last checked') and names the alternative tool for curated synthesis (get_daily_briefing). It also explains the behavior when omitting the cursor, covering initial and subsequent calls.

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

All Horizon AI Intelligence 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?