Lion Reader

list_entries

Read-only

List the user's entries (feed items, newsletter issues and saved articles), newest first by default. Use this to browse or search: filter by subscription, tag, type, read or starred state, sort by date, score or a collection's position (see sortBy), or pass query for relevance-ranked full-text search. Returns items (id, title, summary, url, read/starred state, score, subscription IDs; no body) and nextCursor when there are more: pass it as cursor for the next page. Use get_entry for an entry's content, and count_entries when you only need an unread count.

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": "list_entries"
  }
}

Input Schema

Name	Required	Description
`type`	No	Filter by entry type
`limit`	No	Number of entries per page (max 100)
`query`	No	Full-text search query over entry title and content (relevance-ranked)
`tagId`	No	Filter by tag ID
`cursor`	No	Pagination cursor from previous response
`sortBy`	No	What to sort by. Default: a collection whose articles have positions by position, anything else by date. published (date), readChanged (when last marked read or unread; only entries ever marked, across all subscriptions: not with subscriptionId, tagId, uncategorized or type saved), score (set_entry_scores) or position (a collection's order, set_collection_positions; needs subscriptionId). Entries without a score or position come after those with one, newest first. The first page's `sortable` says whether the list has any scores or positions.
`readOnly`	No	Show only read entries
`sortOrder`	No	Direction of sortBy: newest/oldest for dates, highest/lowest for score, first/last for position (default: the first of each)
`unreadOnly`	No	Show only unread entries
`starredOnly`	No	Show only starred entries
`uncategorized`	No	Show only uncategorized entries
`unstarredOnly`	No	Show only unstarred entries
`subscriptionId`	No	Filter by subscription ID (a feed, a collection or Saved)

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 4, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Annotations only declare readOnlyHint=true and openWorldHint=false; the description goes much further by disclosing the return shape (item fields, explicitly 'no body'), the presence of nextCursor when more results exist, and how to page with cursor. It also surfaces a real constraint — readChanged sorting excludes subscriptionId/tagId/uncategorized/saved-type filters — and notes that `sortable` on the first page signals whether scores or positions exist.

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

Conciseness5/5

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

Three sentences, front-loaded with purpose, then filters/alternatives, then return contract. The middle sentence is dense but every clause names a distinct capability, and the final routing sentence to get_entry/count_entries earns its 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 13 optional parameters and no output schema, the description does the necessary work on return values and pagination. The remaining gap is that it never explains interaction between the boolean filters (e.g., readOnly vs unreadOnly, starredOnly vs unstarredOnly) or which filters can be combined, which matters for a tool with no required arguments.

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 coverage is 100% and the sortBy schema description already carries the readChanged/position constraints verbatim, so the description largely restates structured data. It does add the pointer 'see sortBy' and characterizes `query` as relevance-ranked, but the 13 filter parameters themselves (readOnly vs unreadOnly, starredOnly vs unstarredOnly combinations) get no added meaning beyond their schema text.

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?

Opens with a specific verb and resource ('List the user's entries') and immediately disambiguates what an entry is (feed items, newsletter issues, saved articles), plus the default ordering. It also names the two siblings it is not — get_entry for content and count_entries for counts — so an agent can route correctly without opening a schema.

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

Usage Guidelines5/5

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

Explicitly states the use case ('browse or search') and enumerates the ways to narrow results (subscription, tag, type, read/starred state, sort, or full-text query). It names alternatives with their selecting conditions: get_entry for an entry's content, count_entries when only an unread count is needed.

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

All Lion Reader 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.