Skip to main content
Glama
server-noonien

server-noonien

Official

Find Duplicates

find_duplicates
Read-onlyIdempotent

Propose entity pairs that may describe the same thing, compared by normalized name or by content, so you can review and merge duplicates you would otherwise miss.

Instructions

Propose pairs of entities that may be the same thing, so merge_entities can be used on a pair you would not have noticed. With by: "name" the names are compared after case, spacing, punctuation and a known suffix such as .service are normalised, and overlapping observations raise the score; with by: "content" the observations are compared instead, which is how one fact written twice under two names is found. It is read-only. A score is a hint, not a verdict: read both entities before merging them.

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": "find_duplicates"
  }
}

Input Schema

NameRequiredDescriptionDefault
byNoWhat to compare: name (default) or content
limitNoThe most pairs to return, 20 by default, best first
thresholdNoThe lowest score to report, 0.75 by default

Output Schema

NameRequiredDescriptionDefault
pairsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.3.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so "It is read-only" is largely redundant, but the description adds real behavioral context beyond them: the normalisation rules applied to names (case, spacing, punctuation, known suffixes like .service), that overlapping observations raise the score, and the caution that "a score is a hint, not a verdict." It does not discuss ordering or how many pairs typically surface, but the annotations carry the safety profile.

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?

The purpose is front-loaded and the two modes are then differentiated in parallel structure. The sentence enumerating normalisation rules is dense but each clause is informative; the only slack is the redundant "It is read-only" given the annotations.

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

Completeness5/5

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

With an output schema present, return values need no explanation, and defaults for limit and threshold live in the schema. The description supplies exactly the missing layer: what the score means, how each mode behaves, and what to do with a candidate pair.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so a baseline of 3 applies, but the description goes beyond the enum labels by explaining what each by value actually compares and what evidence each mode weighs. limit and threshold are left entirely to their schema descriptions, which is acceptable given full coverage.

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?

"Propose pairs of entities that may be the same thing" gives a specific verb and resource, and the description immediately names merge_entities as the downstream consumer, which separates it from sibling read tools like search_nodes or read_graph. An agent can tell what it produces (candidate pairs) without opening the schema.

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

Usage Guidelines4/5

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

It explains which mode to pick: by "name" for normalised name matching plus overlapping observations, by "content" for the same fact written twice under two names. It also states the downstream action (merge_entities) and warns to read both entities first. It stops short of an explicit when-not-to-use or a note on when a different sibling is preferable, so it is strong context without full exclusion guidance.

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