FeedKeeper RSS/Atom reader and remote MCP Server

Bookmark articles for later

bookmark_item

Save one or more articles for permanent retention so their full text and images survive automatic cleanup and feed unsubscription. Accepts single or batch item IDs.

Instructions

Bookmarks (stars) one or more articles for permanent retention. Bookmarked articles retain full text and images and survive automatic retention cleanup and feed unsubscription. Idempotent. Returns { ok: true, updated: number }.

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": "bookmark_item"
  }
}

Input Schema

Name	Required	Description	Default
`itemId`	No	A single item ID to target
`itemIds`	No	An array of up to 200 item IDs to target in batch

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.36.4Nov 9, 2026

changedInput schema / properties / itemId / description

Previous value: -"A single item ID"New value: +"A single item ID to target"

changedInput schema / properties / itemIds / description

Previous value: -"Up to 200 item IDs"New value: +"An array of up to 200 item IDs to target in batch"

First observedv0.36.3Nov 9, 2026

TDQS

A4/5.0

Behavior4/5

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

With no annotations at all, the description carries the full burden and does well: it discloses idempotency, the permanence guarantee, survival of automatic retention cleanup and feed unsubscription, and it even gives the return shape. Gaps remain around auth requirements, error behavior, and what happens on invalid or already-deleted item IDs.

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?

Four short sentences, front-loaded with the core action and then the consequences, with zero redundant wording. The return-shape note is compact and useful rather than verbose.

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 simple two-parameter mutation with no annotations and no output schema, the description covers effect, durability, idempotency, and return value, which is nearly everything an agent needs. It falls just short on the itemId/itemIds interaction and failure modes.

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 the schema already documents both itemId and itemIds including the 200-item batch cap. The phrase 'one or more articles' hints that either parameter suits, but it does not resolve whether both may be supplied together or which takes precedence, so it adds little beyond the schema baseline.

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?

States a specific verb (bookmarks/stars) and resource (articles), plus scope (one or more) and the persistence semantics that define the operation. It is clearly distinguishable from the sibling unbookmark_item.

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 through the permanence framing ('permanent retention', survives retention cleanup and feed unsubscription), which tells the agent the effect of calling it. However, it never names an alternative such as save_to_inbox or unbookmark_item, nor states when not to use it, so routing between similar siblings is left to inference.

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