Skip to main content
Glama
catalog-mcp

catalog-mcp

by Yehiak

Find near-duplicate listings

find_near_duplicates
Read-onlyIdempotent

Detect likely duplicate product listings before adding them by comparing a draft title or product ID against catalog items, using similarity, title overlap, model/part numbers, and platform checks.

Instructions

Find listings that are probably the same item as a product (or a draft title), e.g. one part sold by several sellers.

Each candidate carries the evidence: embedding similarity, title word overlap, shared model or part numbers, and a platform check so a PS5 and a Switch edition of one game count as variants, not duplicates.

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_near_duplicates"
  }
}

Input Schema

NameRequiredDescriptionDefault
limitNoMaximum number of candidates.
titleNoA new listing title to check against the catalog before adding it. Give this or `product_id`.
product_idNoFind listings that duplicate this product. Give this or `title`, not both.
same_categoryNoOnly look in the query product's category.
min_similarityNoCosine similarity cut-off (0.5-1.0). 0.85 is a good default; raise it for fewer, surer hits.

Output Schema

NameRequiredDescriptionDefault
candidatesYes
query_titleYes
query_product_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish read-only, idempotent, non-destructive behavior, so the description only needs to add context beyond that. It usefully discloses that candidates carry evidence such as embedding similarity, title overlap, shared part numbers, and a platform check that distinguishes variants from duplicates. It does not discuss ordering or rate limits, but the output schema likely covers return structure.

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?

The description is two compact sentences, front-loaded with the core purpose and followed by useful evidence details. Every sentence contributes relevant information without repetition or 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 read-only lookup tool with rich annotations, full schema coverage, and an output schema, the description is largely complete: it explains the purpose and the evidence returned. It could more explicitly state the one-of input requirement for product_id or title and mention tuning via min_similarity, but those are available in the schema.

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 all five parameters. The description adds conceptual meaning by framing inputs as a product or draft title and by explaining duplicate-vs-variant logic, but it does not add detail about min_similarity, same_category, or limit beyond what the schema provides. Baseline 3 is appropriate.

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?

The description states a specific verb and resource: finding listings that are probably the same item as a product or draft title. It also clarifies the duplicate-vs-variant distinction with a concrete platform example. It does not explicitly differentiate itself from sibling tools such as search_products or compare_products, 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?

Usage is implied through examples like 'one part sold by several sellers' and checking a draft title, but there is no explicit when-to-use or when-not-to-use guidance versus alternatives. The agent can infer this is for duplicate detection, but the description does not route between this and sibling search or comparison tools.

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