Skip to main content
Glama

Search VYKA diamonds

search_diamonds
Read-onlyIdempotent

Returns loose diamonds currently listed on vykadiamonds.com (VYKA, Dubai), natural or lab-grown, with the same selection, order and prices as the website's diamond pages. Use this when the user wants to find or compare diamonds VYKA sells, by shape, carat, colour, clarity or budget. Only stones with a laboratory grading report are returned (natural: GIA, IGI or HRD; lab-grown: also GCAL). Unless the user sets a value, the website's own starting filters apply: natural 0.5 ct and up, colour D–H, clarity VS2 or better, Excellent or Ideal cut where the laboratory grades cut, Very Good or Excellent polish and symmetry; lab-grown 1.0 ct and up, colour D–F, clarity VS1 or better, Excellent or Ideal cut where graded, Excellent polish and symmetry; both: eye-clean, no tinge, returnable, with photo and 360° view, lowest price first. Any value the user gives replaces that default. Limits: at most 10 stones per call; stock changes quickly and a listed stone can sell at any time; AED prices are the charged prices, other currencies are indicative. Does not cover ring settings, finished rings, gemstones or fancy-colour diamonds, and cannot reserve or buy a stone.

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": {
      "type": "<type>"
    },
    "name": "search_diamonds"
  }
}

Input Schema

NameRequiredDescriptionDefault
sortNoprice_low_to_high
typeYesnatural = mined diamonds; lab = lab-grown diamonds.
limitNoHow many stones to return (1–10).
shapeNoOne or more shapes. Leave out for every shape.
currencyNoCurrency of max_price and of the indicative price shown beside the AED price.AED
carat_maxNoLargest carat weight (20 = no upper limit).
carat_minNoSmallest carat weight.
max_priceNoHighest price, in `currency`.
colour_lowestNoLowest colour grade to include, e.g. G for 'G or better'.
clarity_lowestNoLowest clarity grade to include, e.g. VS1 for 'VS1 or better'.
colour_highestNoHighest colour grade to include (D is the highest).
clarity_highestNoHighest clarity grade to include (FL is the highest).

Output Schema

NameRequiredDescriptionDefault
typeYes
countYes
diamondsYes
browse_linkYesThe matching diamond page on vykadiamonds.com.
currency_noteYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare read-only, idempotent, closed-world and non-destructive, but the description adds substantial context beyond them: the website's default filter sets for natural vs lab-grown when the user gives no values, 'any value the user gives replaces that default', the 10-stones-per-call cap, live stock volatility, and that AED is the charged price while other currencies are indicative. Those are exactly the behavioural facts an agent needs to set expectations and avoid over-promising.

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?

It is a long definition, but it is front-loaded with what is returned and every sentence carries information (defaults, limits, currency caveat, exclusions). The dense enumeration of default filter rules in a single paragraph is harder to scan than a short bulleted list would be, which keeps it just short of top marks.

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?

For a 12-parameter search tool with an output schema and rich annotations, the description covers the remaining gaps: default filter behaviour, result ordering, per-call cap, price semantics and out-of-scope inventory. Nothing an agent needs to call it correctly or to set user expectations is missing.

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 92%, so the schema already carries most parameter meaning and a baseline of 3 would apply. The description still adds real value on top: it explains the semantic effect of omitting a parameter (website defaults apply), that user-supplied values replace rather than merge with defaults, and the indicative-vs-charged currency distinction, which the schema does not state.

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 and resource ('Returns loose diamonds currently listed on vykadiamonds.com'), names the vendor and location, and scopes the inventory (natural or lab-grown, graded stones only). It also explicitly distinguishes itself from adjacent offerings (ring settings, finished rings, gemstones, fancy-colour diamonds), so an agent can tell this is the loose-stone search tool rather than a detail or report lookup.

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?

Gives a clear trigger ('Use this when the user wants to find or compare diamonds VYKA sells, by shape, carat, colour, clarity or budget') plus strong negative scope (not settings, not fancy-colour, cannot reserve or buy). It does not name the sibling tools (get_diamond, check_report, vyka_score) as alternatives, so an agent must infer that single-stone lookups belong elsewhere.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources