Trending Now

Daily trend digest for a niche

trending_digest

Read-onlyIdempotent

Use this when the user wants a daily digest or content ideas for a niche, such as "give me today's AI digest" or "content ideas for marketing". Pass niche (ai, developer-tools, startups, marketing, ecommerce, security, or the user's own words, read as the closest niche or a keyword search; leave it out for everything) and optionally limit. Returns the top posts of the last 3 days that are still on their sources' lists, the top 5 for each source, rising keywords, post counts per niche, how the niche was read (match) and a link to the digest page.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "niche": "developer-tools"
    },
    "name": "trending_digest"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	Most posts returned (default 20)
`niche`	No	A niche (ai, developer-tools, startups, marketing, ecommerce, security) or the user's own words. Other words go to the closest niche, or else become a keyword search over the same sources; the answer's match says which. Leave it out for everything.

Output Schema

Name	Required	Description
`note`	Yes
`page`	Yes
`as_of`	Yes	ISO 8601 time the data was published by its source or fetched from it. A cached answer keeps the time of its fetch.
`match`	Yes	How requested was read: as given, the closest niche, or a keyword search
`niche`	Yes	The niche used: a slug, all, or null for a keyword search
`posts`	Yes
`title`	Yes
`niches`	Yes
`source`	Yes	Who the data comes from, to cite and to check it against.
`status`	Yes
`sources`	Yes
`not_read`	Yes
`by_source`	Yes
`requested`	Yes	The niche text the call sent
`rising_keywords`	Yes
`posts_considered`	Yes
`untrusted_source`	Yes
`keywords_baseline`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedNov 4, 2026

addedOutput schema / properties / by_source / additionalProperties / items / properties / rank

Added value: +{
+  "description": "1-based place across all sources: heat, then the newer post at equal heat",
+  "type": "integer"
+}

changedOutput schema / properties / by_source / additionalProperties / items / required

Previous value: -[
-  "source",
-  "source_name",
-  "title",
-  "url",
-  "published_at",
-  "engagement",
-  "unit",
-  "velocity_per_hour",
-  "velocity_basis",
-  "heat",
-  "niches"
-]New value: +[
+  "rank",
+  "source",
+  "source_name",
+  "title",
+  "url",
+  "published_at",
+  "engagement",
+  "unit",
+  "velocity_per_hour",
+  "velocity_basis",
+  "heat",
+  "niches"
+]

addedOutput schema / properties / posts / items / properties / rank

Added value: +{
+  "description": "1-based place across all sources: heat, then the newer post at equal heat",
+  "type": "integer"
+}

changedOutput schema / properties / posts / items / required

Previous value: -[
-  "source",
-  "source_name",
-  "title",
-  "url",
-  "published_at",
-  "engagement",
-  "unit",
-  "velocity_per_hour",
-  "velocity_basis",
-  "heat",
-  "niches"
-]New value: +[
+  "rank",
+  "source",
+  "source_name",
+  "title",
+  "url",
+  "published_at",
+  "engagement",
+  "unit",
+  "velocity_per_hour",
+  "velocity_basis",
+  "heat",
+  "niches"
+]

Changed8 schema fields changedOct 22, 2026

changedInput schema / properties / niche / description

Previous value: -"One niche; leave it out for everything"New value: +"A niche (ai, developer-tools, startups, marketing, ecommerce, security) or the user's own words. Other words go to the closest niche, or else become a keyword search over the same sources; the answer's match says which. Leave it out for everything."

removedInput schema / properties / niche / enum

Removed value: -[
-  "ai",
-  "developer-tools",
-  "startups",
-  "marketing",
-  "ecommerce",
-  "security"
-]

addedInput schema / properties / niche / maxLength
```
Added value: +80
```

addedOutput schema / properties / match

Added value: +{
+  "description": "How requested was read: as given, the closest niche, or a keyword search",
+  "enum": [
+    "all",
+    "niche",
+    "nearest_niche",
+    "words"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / niche / description

Added value: +"The niche used: a slug, all, or null for a keyword search"

changedOutput schema / properties / niche / type

Previous value: -"string"New value: +[
+  "string",
+  "null"
+]

addedOutput schema / properties / requested

Added value: +{
+  "description": "The niche text the call sent",
+  "type": [
+    "string",
+    "null"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "status",
-  "posts_considered",
-  "posts",
-  "rising_keywords",
-  "keywords_baseline",
-  "sources",
-  "not_read",
-  "niche",
-  "title",
-  "niches",
-  "by_source",
-  "page",
-  "untrusted_source",
-  "note",
-  "as_of",
-  "source"
-]New value: +[
+  "status",
+  "posts_considered",
+  "posts",
+  "rising_keywords",
+  "keywords_baseline",
+  "sources",
+  "not_read",
+  "niche",
+  "title",
+  "requested",
+  "match",
+  "niches",
+  "by_source",
+  "page",
+  "untrusted_source",
+  "note",
+  "as_of",
+  "source"
+]

Changed4 schema fields changedOct 19, 2026

changedOutput schema / properties / as_of / description

Previous value: -"When the sources were last read"New value: +"ISO 8601 time the data was published by its source or fetched from it. A cached answer keeps the time of its fetch."

changedOutput schema / properties / as_of / type

Previous value: -[
-  "string",
-  "null"
-]New value: +"string"

addedOutput schema / properties / source

Added value: +{
+  "description": "Who the data comes from, to cite and to check it against.",
+  "properties": {
+    "name": {
+      "type": "string"
+    },
+    "url": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "name",
+    "url"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "status",
-  "as_of",
-  "posts_considered",
-  "posts",
-  "rising_keywords",
-  "keywords_baseline",
-  "sources",
-  "not_read",
-  "niche",
-  "title",
-  "niches",
-  "by_source",
-  "page",
-  "untrusted_source",
-  "note"
-]New value: +[
+  "status",
+  "posts_considered",
+  "posts",
+  "rising_keywords",
+  "keywords_baseline",
+  "sources",
+  "not_read",
+  "niche",
+  "title",
+  "niches",
+  "by_source",
+  "page",
+  "untrusted_source",
+  "note",
+  "as_of",
+  "source"
+]

First observedOct 16, 2026

TDQS

A3.6/5.0

Behavior3/5

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

Annotations already establish readOnly, idempotent, non-destructive and closed-world behavior, so the description only needs to add context. It does add useful freshness semantics ('last 3 days that are still on their sources' lists', 'top 5 for each source') that the annotations cannot convey, but it spends most of its length enumerating return fields that the output schema already documents.

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

Conciseness3/5

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

The usage trigger is correctly front-loaded, but the remainder is a single run-on sentence that bundles parameter rules and a long return-value inventory together. Much of that inventory duplicates the output schema, so several clauses do not earn their place.

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?

With an output schema present and annotations covering the safety profile, the description needs to carry usage and parameter resolution, which it does thoroughly, including zero-argument behavior ('leave it out for everything'). The one real omission is sibling disambiguation against 'trending', which matters given the overlap in topic.

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%, so both parameters are already documented, and the description largely restates the same resolution rule (closest niche, else keyword search, with 'match' reporting which). It adds only marginal value, such as the example user phrasings that would land in the niche field, so the baseline of 3 is right.

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?

The description states a specific verb and resource: produce a daily digest / content ideas for a niche, backed by a concrete scope (top posts of the last 3 days, top 5 per source, rising keywords). It is clear what the tool does, but it never distinguishes itself from the sibling tool 'trending', which an agent could easily confuse with a trend-oriented digest.

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?

It opens with an explicit trigger condition ('Use this when the user wants a daily digest or content ideas for a niche') and supplies two literal example utterances, which is strong routing guidance. It stops short of stating when NOT to use it or naming the alternative sibling to pick instead, so it falls below a 5.

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

All Trending Now 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.