Skip to main content
Glama
FeedKeeper RSS/Atom reader and remote MCP Server

FeedKeeper RSS/Atom reader and remote MCP Server

Search articles by keyword or phrase

search_items

Search article titles and summaries across accessible RSS/Atom items, then narrow results by feed, folder, bookmark status, or publication date. Use read-only queries to find matching articles.

Instructions

Searches article titles and summaries using SQLite FTS5 full-text search across all accessible items. Returns matching articles matching the query phrase, with optional feed, folder, bookmark, and date filters. Safe read-only search.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_items"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of search results to return (1 to 200, default: 50)
queryYesThe search term or phrase to find in article titles and content summaries
sinceNoFilter for items published at or after this ISO date or date-time
untilNoFilter for items published at or before this ISO date or date-time
feedIdNoOptional feed ID filter
folderIdNoOptional folder ID filter
bookmarkedOnlyNoWhen true, restricts search to bookmarked items

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed7 schema fields changedv0.36.4
    • addedInput schema / properties / bookmarkedOnly / description
      Added value: +"When true, restricts search to bookmarked items"
    • addedInput schema / properties / feedId / description
      Added value: +"Optional feed ID filter"
    • addedInput schema / properties / folderId / description
      Added value: +"Optional folder ID filter"
    • addedInput schema / properties / limit / description
      Added value: +"Maximum number of search results to return (1 to 200, default: 50)"
    • addedInput schema / properties / query / description
      Added value: +"The search term or phrase to find in article titles and content summaries"
    • changedInput schema / properties / since / description
      Previous value: -"Only items published at or after this ISO date or date-time"New value: +"Filter for items published at or after this ISO date or date-time"
    • changedInput schema / properties / until / description
      Previous value: -"Only items published at or before this ISO date or date-time"New value: +"Filter for items published at or before this ISO date or date-time"
  2. First observedv0.36.3

TDQS

A3.5/5.0
Behavior3/5

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

No annotations exist, so the description carries the full behavioral burden; it does state 'Safe read-only search', which usefully declares the safety profile, and it discloses that only titles and summaries are searched (a meaningful limit versus fetch_full_text). It omits result ordering/relevance ranking, pagination behavior, and whether the query string is interpreted as FTS5 syntax (operators, phrase quoting), which matters for a full-text search tool.

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?

Two sentences, front-loaded with what is searched, then filters, then safety. Minor redundancy in 'Returns matching articles matching the query phrase' where 'matching' appears twice, but no substantive filler.

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?

For a 7-parameter search tool with no output schema and no annotations, the description covers the resource scope, the filter set, and the read-only safety profile, while the schema fully documents parameters. The remaining gap is how results are ordered or ranked and whether the query supports FTS5 operators, which an agent would want before relying on results.

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 every parameter (limit, query, since, until, feedId, folderId, bookmarkedOnly) is already documented. The description only restates the filter categories ('feed, folder, bookmark, and date filters') without adding semantics such as inclusive date boundaries or default limit behavior, so the 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 ('Searches') and the searched fields ('article titles and summaries') and names the underlying mechanism (SQLite FTS5 full-text search) across 'all accessible items'. It clearly is a keyword search rather than a listing, though it never names a sibling such as list_items or fetch_full_text to draw the boundary explicitly.

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 'using SQLite FTS5 full-text search' and the query requirement, so an agent can infer this is the tool for keyword/phrase lookup. However, there is no explicit when-to-use vs. when-not guidance and no mention of the sibling list_items for unfiltered enumeration, leaving the agent to reason about the choice.

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