Pure Report — Neutral News

Search neutral news

search_news

Read-only

Search Pure Report's neutral, bias-scored news. Returns articles rewritten to remove loaded language; bias_score (0-100) rates the ORIGINAL source reporting before neutralization (0 = wire-neutral, 100 = advocacy), NOT the returned rewrite, which is neutral by design. Each result also lists the event(s) it belongs to — pass an event slug to get_event for the neutral writeup or compare_coverage for cross-outlet framing. Ranked by relevance and recency.

Input Schema

TableJSON Schema

Name	Required	Description
`limit`	No	Max results to RETURN, 1-40 (default 15). Does not affect total_matches, which always reports how many articles matched.
`query`	Yes	Keywords or phrase, e.g. "Iran sanctions" or "2026 election".
`topic`	No	Optional topic-slug filter. An unrecognized value searches all topics and returns a warning.
`offset`	No	Skip this many matches — page through results beyond the 40-row limit. The response echoes offset/returned/next_offset; next_offset is null on the last page.
`published_after`	No	Only articles published on/after this date. 'YYYY-MM-DD' or full ISO. Use with published_before to bound a period, e.g. coverage during June.
`published_before`	No	Only articles published on/before this date. 'YYYY-MM-DD' or full ISO.

Output Schema

TableJSON Schema

Name	Required	Description
`query`	Yes
`offset`	No
`results`	Yes
`warning`	No
`returned`	No
`next_offset`	No
`applied_topic`	No
`total_matches`	Yes	TOTAL articles matching the query, independent of `limit` — not the number returned. len(results) < total_matches means more exist.
`result_composition`	No	Factual description of what the returned set is ABOUT. Search is lexical, so every query term appears in every result; this reports whether a term is the SUBJECT (title/entities/lede) or only a body mention, plus the entity distribution. Measurements only — no verdict.

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedAug 2, 2026

addedInput schema / properties / offset

Added value: +{
+  "description": "Skip this many matches — page through results beyond the 40-row limit. The response echoes offset/returned/next_offset; next_offset is null on the last page.",
+  "type": "integer"
+}

addedInput schema / properties / published_after

Added value: +{
+  "description": "Only articles published on/after this date. 'YYYY-MM-DD' or full ISO. Use with published_before to bound a period, e.g. coverage during June.",
+  "type": "string"
+}

addedInput schema / properties / published_before

Added value: +{
+  "description": "Only articles published on/before this date. 'YYYY-MM-DD' or full ISO.",
+  "type": "string"
+}

addedOutput schema / properties / next_offset

Added value: +{
+  "type": [
+    "integer",
+    "null"
+  ]
+}

addedOutput schema / properties / offset
```
Added value: +{
+  "type": "integer"
+}
```
addedOutput schema / properties / returned
```
Added value: +{
+  "type": "integer"
+}
```

Changed1 schema field changedAug 2, 2026

addedOutput schema / properties / result_composition

Added value: +{
+  "description": "Factual description of what the returned set is ABOUT. Search is lexical, so every query term appears in every result; this reports whether a term is the SUBJECT (title/entities/lede) or only a body mention, plus the entity distribution. Measurements only — no verdict.",
+  "type": "object"
+}

Changed2 schema fields changedAug 2, 2026

changedInput schema / properties / limit / description

Previous value: -"Max results, 1-40 (default 15)."New value: +"Max results to RETURN, 1-40 (default 15). Does not affect total_matches, which always reports how many articles matched."

addedOutput schema / properties / total_matches / description

Added value: +"TOTAL articles matching the query, independent of `limit` — not the number returned. len(results) < total_matches means more exist."

Changed1 schema field changedJul 13, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "applied_topic": {
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "query": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "properties": {
+          "bias_score": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "events": {
+            "items": {
+              "properties": {
+                "name": {
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "slug": {
+                  "type": "string"
+                }
+              },
+              "type": "object"
+            },
+            "type": "array"
+          },
+          "id": {
+            "type": "integer"
+          },
+          "published_at": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "source": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "summary": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "title": {
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total_matches": {
+      "type": "integer"
+    },
+    "warning": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "query",
+    "total_matches",
+    "results"
+  ],
+  "type": "object"
+}

First observedJul 13, 2026

TDQS

A4.4/5.0

Behavior5/5

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

The description goes significantly beyond the readOnlyHint annotation by explaining that returned articles are rewritten to remove loaded language, and crucially that bias_score rates the ORIGINAL source, not the neutralized rewrite. This prevents a major misunderstanding. It also discloses that results include associated events and that ordering is by relevance and recency, providing rich behavioral context.

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?

The description is a single dense paragraph but every sentence adds value: it explains the neutralization, bias_score nuance, event links, and ranking. It is slightly long but not bloated; the structure could be improved with clearer sentence breaks, but it remains efficient and front-loaded with the core purpose.

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 complexity (bias_score semantics, event associations, pagination) and that an output schema exists, the description covers the key behavioral nuances that could trip up an agent: the bias_score scope, the existence of event slugs, and the linking to related tools. With a detailed schema also present, nothing important is left unexplained.

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% and each parameter has detailed, self-explanatory descriptions (e.g., offset explains next_offset pagination, limit notes total_matches). The description adds no additional parameter-specific syntax or semantics beyond what the schema already covers, so the baseline 3 is appropriate.

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 begins with 'Search Pure Report's neutral, bias-scored news,' clearly stating the action (search) and resource (Pure Report's neutral, bias-scored news). It distinguishes itself from siblings by explaining that results include event slugs which can be passed to get_event or compare_coverage, making the tool's specific role clear.

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?

The description provides clear context for when to use the tool: searching for neutral, bias-scored news. It explicitly directs users to get_event for neutral writeups and compare_coverage for cross-outlet framing when they have an event slug, offering alternatives. However, it doesn't explicitly state when not to use search_news (e.g., for fetching a known article via get_article), so it lacks full exclusion guidance.

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

All Pure Report — Neutral News 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?