Skip to main content
Glama
bookmark-organizer

bookmark-organizer

by dpfcarlos

Remove duplicate bookmarks

remove_duplicates

Deletes duplicate bookmarks and keeps one copy of each page, defaulting to a dry run so you can review changes before deleting.

Instructions

Keeps one copy of each page and deletes the others. Dry run by default.

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": "remove_duplicates"
  }
}

Input Schema

NameRequiredDescriptionDefault
keepNoWhich copy to keep. "first" = the one that appears first walking from the bookmarks bar.oldest
forceNoWrite even if the browser seems to be open. Avoid: an open browser overwrites the file when it closes.
dry_runNoWhen true (default) nothing is written; the tool only reports what would change. Show that to the user and call again with dry_run=false after they confirm.
profileNoProfile id from list_profiles (e.g. "chrome:Default", "edge:Profile 1") or the full path to a Bookmarks file. Optional when only one profile exists.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden; it does disclose the destructive action ('deletes the others') and the default no-write mode, which is valuable. It omits irreversibility, backup recommendations, and the open-browser overwrite hazard that only appears in the schema's force parameter, so material risk context is missing from the description itself.

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?

Two short sentences with the action first and the safety-relevant default second, no filler. Every clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, zero-annotation, no-output-schema tool, the description says what is destroyed and that it is dry-run-first, which is the core minimum. It leaves the agent without the return/report shape, any backup/recovery note, or the open-browser caveat, all of which an agent needs before calling with dry_run=false.

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 baseline of 3 applies; the enum values for keep, the force warning, and the dry_run workflow are all fully documented in the schema. The description's only parameter-adjacent statement, 'Dry run by default,' merely restates a schema default.

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 and resource: it deletes duplicate bookmark pages while keeping one copy, which an agent can distinguish from find_duplicates or delete_all_bookmarks by the word 'deletes'. It does not explicitly name a sibling or scope the operation (profile-wide vs folder), so it stops short of 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?

'Dry run by default' hints at the intended workflow but the actual when/when-not guidance (show report to user, then re-call with dry_run=false) lives only in the schema. There is no explicit contrast with find_duplicates or delete_bookmarks, leaving the agent to infer which tool to pick.

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