New Runtime public records

What changed since a date, against what New Runtime already knew

what_changed

Read-onlyIdempotent

Use when you already know a topic and need only what changed since a date (your last run, a report date): which AI-engineering patterns and shifts got stronger or weaker, what became obsolete, which forecasts resolved, and which new items are new facts versus new angles on known stories, plus what still holds. Saves re-reading and re-deduplicating the web. Free, no auth. Example: {"since": "2026-09-01", "topic": "mcp"}.

Input Schema

Name	Required	Description	Default
`since`	No	ISO date or date-time of your last known state, e.g. 2026-09-01. Default: 7 days ago; at most 90 days back.
`topic`	No	Optional topic slug or name (agents, coding-agents, MCP...).

Output Schema

Name	Required	Description
`next`	No	Suggested next call.
`since`	Yes	Window start, YYYY-MM-DD.
`topic`	No	Topic filter, or null.
`until`	Yes	Window end, YYYY-MM-DD.
`counts`	Yes	Counts per kind of change (strengthened, weakened, revised, new_records, retired, new_facts, ...).
`method`	No	How changes are detected.
`retired`	No	Records retired in the window.
`verdict`	Yes	One-sentence summary of what changed.
`forecasts`	No	Forecasts resolved and opened in the window.
`new_records`	No	Records first published in the window.
`still_holds`	No	Known records re-verified and unchanged.
`new_evidence`	No	New facts, new angles and evidence updates.
`state_changes`	No	Known records that were strengthened, weakened or revised, each with evidence.
`field_notes_and_analyses`	No	Field Notes and analyses published in the window.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 27, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "counts": {
+      "description": "Counts per kind of change (strengthened, weakened, revised, new_records, retired, new_facts, ...).",
+      "properties": {},
+      "type": "object"
+    },
+    "field_notes_and_analyses": {
+      "description": "Field Notes and analyses published in the window.",
+      "items": {
+        "properties": {
+          "date": {
+            "description": "Record date, YYYY-MM-DD."
+          },
+          "json": {
+            "description": "Machine-readable twin of the page."
+          },
+          "title": {
+            "description": "Record title."
+          },
+          "url": {
+            "description": "newruntime.com page; pass it to get_record."
+          },
+          "why": {
+            "description": "One line on why the item matters."
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "forecasts": {
+      "description": "Forecasts resolved and opened in the window.",
+      "properties": {},
+      "type": "object"
+    },
+    "method": {
+      "description": "How changes are detected.",
+      "type": "string"
+    },
+    "new_evidence": {
+      "description": "New facts, new angles and evidence updates.",
+      "properties": {},
+      "type": "object"
+    },
+    "new_records": {
+      "description": "Records first published in the window.",
+      "type": "array"
+    },
+    "next": {
+      "description": "Suggested next call.",
+      "type": "string"
+    },
+    "retired": {
+      "description": "Records retired in the window.",
+      "type": "array"
+    },
+    "since": {
+      "description": "Window start, YYYY-MM-DD.",
+      "type": "string"
+    },
+    "state_changes": {
+      "description": "Known records that were strengthened, weakened or revised, each with evidence.",
+      "properties": {},
+      "type": "object"
+    },
+    "still_holds": {
+      "description": "Known records re-verified and unchanged.",
+      "items": {
+        "properties": {
+          "confidence": {
+            "description": "Confidence."
+          },
+          "date": {
+            "description": "Record date, YYYY-MM-DD."
+          },
+          "json": {
+            "description": "Machine-readable twin of the page."
+          },
+          "last_verified": {
+            "description": "Last verification date."
+          },
+          "title": {
+            "description": "Record title."
+          },
+          "url": {
+            "description": "newruntime.com page; pass it to get_record."
+          },
+          "why": {
+            "description": "One line on why the item matters."
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "topic": {
+      "description": "Topic filter, or null."
+    },
+    "until": {
+      "description": "Window end, YYYY-MM-DD.",
+      "type": "string"
+    },
+    "verdict": {
+      "description": "One-sentence summary of what changed.",
+      "type": "string"
+    }
+  },
+  "required": [
+    "since",
+    "until",
+    "counts",
+    "verdict"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedSep 27, 2026
- addedInput schema / properties / since / examples
```
Added value: +[
+  "2026-09-01",
+  "2026-09-20T00:00:00Z"
+]
```
- addedInput schema / properties / topic / examples
```
Added value: +[
+  "mcp",
+  "coding-agents",
+  "agent-memory"
+]
```
AddedSep 26, 2026

TDQS

A4/5.0

Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the description's job is additive — and it does add: 'Free, no auth' and the promise that it saves re-reading and re-deduplicating the web. It also enumerates the shape of the returned delta (stronger/weaker, obsolete, resolved, new-fact vs new-angle, still-holds), which goes beyond the hints.

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?

Front-loaded with the usage trigger and ends with a compact call example, so the important part is read first. The middle is a long comma-chained enumeration that could be trimmed, but it is all substantive content rather than filler.

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 only two optional parameters, full schema coverage, a rich annotation set, and an output schema that documents return values, the description covers everything an agent needs: when to reach for it, what category of answer it produces, and that no auth is required.

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 description coverage is 100%, including the default (7 days ago) and the 90-day lookback bound, so the schema already carries parameter meaning. The description only restates the date concept ('since a date') and adds an inline example that duplicates the schema's own examples, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: it returns the delta since a date across AI-engineering patterns, obsolete items, resolved forecasts, and known-vs-new stories. The scope is precise enough to separate it from a general 'what's new' feed, though it never names the sibling `whats_new` or `get_topic_brief` for explicit contrast.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

Opens with a clear when-to-use trigger ('when you already know a topic and need only what changed since a date'), and gives concrete anchor examples (last run, report date). It lacks explicit when-NOT-to-use guidance or a named alternative for the case where the user does not already know the topic.

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

All New Runtime public records tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?