Skip to main content
Glama

Noozra

by com.noozra
OverviewDiscussionsAdmin

Search news

search_news
Read-onlyIdempotent

Search news headlines from the last 28 days across 70+ news sites, best match first. Typos and partial words still match. Nothing older than 28 days is searched, so an empty result means nothing matched in that window, not that the story never happened: say so. Each item's url is the publisher's own article: name the source and link the url when you show it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoHow many articles to return (1 to 100).
queryYesWhat to search for, e.g. "electric cars".
categoryNoOnly this news section. Leave it out for every section.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countYesHow many articles are in articles.
articlesYesBest match first.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "articles": {
+      "description": "Best match first.",
+      "items": {
+        "description": "One article.",
+        "properties": {
+          "category": {
+            "description": "The news section, e.g. world or tech.",
+            "type": "string"
+          },
+          "description": {
+            "description": "The publisher's own short description from its feed; null when the feed has none.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "headline": {
+            "description": "The headline, as the publisher wrote it.",
+            "type": "string"
+          },
+          "id": {
+            "description": "The article's id.",
+            "type": "string"
+          },
+          "published_at": {
+            "description": "When the publisher published it, as an RFC 3339 time in UTC.",
+            "type": "string"
+          },
+          "source": {
+            "description": "The publisher's name.",
+            "type": "string"
+          },
+          "story_id": {
+            "description": "The story the article belongs to: pass it to story_coverage for every news site's coverage. null for an article not yet grouped into a story.",
+            "type": [
+              "string",
+              "null"
+            ]
+          },
+          "url": {
+            "description": "The publisher's own article: link this when you show the headline.",
+            "type": "string"
+          }
+        },
+        "required": [
+          "id",
+          "headline",
+          "url",
+          "published_at",
+          "source",
+          "category",
+          "description",
+          "story_id"
+        ],
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "count": {
+      "description": "How many articles are in articles.",
+      "type": "integer"
+    }
+  },
+  "required": [
+    "count",
+    "articles"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4/5.0
Behavior5/5

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

Annotations already declare safe read behavior, but the description adds substantial non-obvious traits: typo and partial-word matching, the hard 28-day cutoff, the interpretation of an empty result (nothing matched in-window, not that the story never happened), and the provenance of each url. This is rich context beyond what annotations provide.

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?

Four dense sentences, front-loaded with what the tool searches and its ordering, then the matching/window caveats. Every sentence is functional, though the closing presentation instruction ('name the source and link the url') sits slightly apart from core selection criteria.

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?

An output schema exists and annotations carry the safety profile, so return-value explanation is unnecessary. The description covers the window, matching behavior, empty-result meaning, and url provenance — everything an agent needs to call and report correctly.

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% for all three parameters (query, limit, category) including the enum values, so the schema does the heavy lifting. The description adds no syntax, format, or matching detail for the parameters themselves, 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 (search news headlines) plus concrete scope: 28-day window, 70+ sites, best-match ordering. This distinguishes it from latest_news and story_coverage by implication, but no sibling is named explicitly, so sibling differentiation is left to inference.

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

Usage Guidelines3/5

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

Usage is implied by the search-query framing and the temporal window, and the description does instruct the agent how to handle empty results and how to present items. However, it never says when to prefer this tool over latest_news or story_coverage, so the when/when-not guidance is only implied.

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

All Noozra toolsInspect
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