Skip to main content
Glama
Karakeep MCP server

Karakeep MCP server

by karakeep-app

create-highlight

Create a text highlight on a bookmark using character offsets from its readable content, with optional color and note metadata.

Instructions

Create a text highlight on a bookmark using character offsets from the bookmark's readable content.

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": {
      "bookmarkId": "<bookmarkId>",
      "startOffset": "<startOffset>",
      "endOffset": "<endOffset>",
      "text": "<text>",
      "note": "<note>"
    },
    "name": "create-highlight"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteYesAn optional note attached to the highlight.
textYesThe highlighted text, or null if unavailable.
colorNoHighlight color. Defaults to yellow.
endOffsetYesZero-based exclusive character offset.
bookmarkIdYesThe id of the bookmark to highlight.
startOffsetYesZero-based inclusive character offset.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changedv0.35.0
    • changedInput schema / $schema
      Previous value: -"http://json-schema.org/draft-07/schema#"New value: +"https://json-schema.org/draft/2020-12/schema"
    • removedInput schema / properties / note / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / note / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedInput schema / properties / text / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedInput schema / properties / text / type
      Added value: +[
      +  "string",
      +  "null"
      +]
  2. Addedv0.33.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false and destructiveHint=false, so the safety profile is covered. Beyond that, the description discloses the non-obvious behavioral constraint that offsets are anchored to the bookmark's readable content rather than its source, which is exactly the kind of context structured fields cannot carry. It still omits what happens on out-of-range offsets or duplicate highlights.

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?

One sentence, front-loaded with the action and the coordinate-system qualifier attached to it; nothing is wasted. It is perhaps slightly too terse for a 5, since a second clause on the readable-content prerequisite would have helped at minimal cost.

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 6 parameters at full schema coverage and no output schema, the definition covers the essential insight an agent needs to call this correctly. Residual gaps are modest: the return value of the created highlight and behavior for conflicting or overlapping offsets are unstated.

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%, so the per-parameter descriptions already define startOffset/endOffset as zero-based inclusive/exclusive integers. The description's only added value is establishing the frame of reference ('readable content'), which tells the agent these offsets must not be computed against raw HTML; it says nothing about color, note, or text.

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?

Names a specific verb and resource ('Create a text highlight on a bookmark') and adds the mechanism ('using character offsets from the bookmark's readable content'), which distinguishes it from create-bookmark and update-highlight. It never names a sibling explicitly, so it falls short of a 5.

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?

There is an implicit workflow hint: offsets come from the bookmark's readable content, implying the agent must first retrieve that content. There is no explicit when-to-use, no exclusion versus update-highlight or create-bookmark, and no statement of prerequisites or ordering.

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