Skip to main content
Glama

Get articles

get_articles
Read-onlyIdempotent

Fetches articles from a feed, folder, tag, or all items, with filtering by read/unread/starred status and date range; supports pagination and compact triage output.

Instructions

Fetch articles from a feed, folder, tag, or all items. Supports filtering by read/unread/starred status and date range. Costs 1 Zone 1 request per page plus 1 for total_count (disable with include_total=false). total_count is one IDs page of at most 10000; check total_count_is_exact and total_count_continuation before claiming a full total. Base costs exclude safe-read retries (up to 4 attempts, each counted); honor cached status/cooldown. Never blindly replay uncertain writes. See inoreader://usage for limits, URI examples and prompts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_articles"
  }
}

Input Schema

NameRequiredDescriptionDefault
countNoNumber of articles to fetch (1-100, default 20)
orderNoSort order (default: newest)
sinceNoISO date string - only return articles published after this date
filterNoFilter articles by status
compactNoReturn compact metadata (default false). Use for triage workflows to avoid large responses.
stream_idNoStream ID: feed URL (feed/http://...), folder (user/-/label/Name), system stream (user/-/state/com.google/starred), or saved web pages (user/-/state/com.google/saved-web-pages). Defaults to all items.
continuationNoContinuation token for pagination (from previous response)
include_totalNoInclude total_count of all matching items across pages (default true). Set false to save 1 Zone 1 request.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv1.6.1
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • addedInput schema / properties / compact
      Added value: +{
      +  "description": "Return compact metadata (default false). Use for triage workflows to avoid large responses.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / count / type
      Previous value: -"number"New value: +"integer"
    • addedInput schema / properties / include_total
      Added value: +{
      +  "description": "Include total_count of all matching items across pages (default true). Set false to save 1 Zone 1 request.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / since / maxLength
      Added value: +128
    • addedInput schema / properties / since / minLength
      Added value: +1
    • changedInput schema / properties / stream_id / description
      Previous value: -"Stream ID: feed URL (feed/http://...), folder (user/-/label/Name), or system stream (user/-/state/com.google/starred). Defaults to all items."New value: +"Stream ID: feed URL (feed/http://...), folder (user/-/label/Name), system stream (user/-/state/com.google/starred), or saved web pages (user/-/state/com.google/saved-web-pages). Defaults to all items."
  2. First observedv0.1.0

TDQS

A4/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, non-destructive, but the description adds a concrete cost model (1 Zone 1 request per page plus 1 for total_count), retry accounting (up to 4 attempts, each counted), and crucial caveats that total_count is capped at one IDs page of 10000 and must be checked via total_count_is_exact and total_count_continuation. That is exactly the behavioral context structured fields cannot convey.

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 scope sentence is front-loaded and the cost/pagination warnings are tightly packed, but "Never blindly replay uncertain writes" is irrelevant noise on a read-only listing tool and the inoreader://usage pointer is a slightly unearned closing sentence.

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 eight parameters and no output schema, the description does the heavy lifting on cost, pagination tokens, and total_count trustworthiness, which is sufficient to call the tool correctly. It stops short of describing the article payload shape or the difference between compact and full records, which the schema only partially covers.

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?

Schema coverage is 100%, so the schema already documents all eight parameters and this would baseline at 3. The description still adds value by tying include_total to a concrete request cost and by explaining the truncated nature of the total, which the schema's brief "include total_count of all matching items" does not convey.

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?

"Fetch articles from a feed, folder, tag, or all items" names a specific verb and resource and enumerates the source scopes, which separates it informally from search_articles and get_article_ids. However, it never names those siblings explicitly, so the agent must infer the boundary between listing and keyword search.

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?

It gives real operative guidance — use compact for triage workflows, set include_total=false to save a request, honor cached status/cooldown — but says nothing about when to choose this over search_articles, get_article_ids, get_article_content, or get_saved_items. Usage is implied by capability rather than stated as routing rules.

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