Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

sephora_search

Search Sephora's product catalog by keyword to get products with brand, pricing, rating, and review counts, filtered by brand, price range, rating, or new status.

Instructions

Sephora product search. Searches Sephora's product catalog by keyword, with real page-based pagination. Returns products with brand, pricing, rating, and review count. Sephora's own search never returns a genuine zero-result state for a nonempty keyword -- an unrecognized/nonsense keyword still returns a full, unrelated fallback result set rather than an empty one. price_min/price_max must be provided together (whole dollars) -- upstream silently ignores a one-sided price range rather than filtering or erroring, so this endpoint rejects a one-sided range as invalid instead of passing it through. brand and filter each accept multiple values (OR'd together within the same facet); brand/rating_min/is_new/filter/price_min/price_max can all be combined with each other (AND'd together across different facets).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
pageNoResult page, 1-based, defaults to 1
brandNoOne or more exact brand names to filter to (OR'd together); repeat the param for multiple values
queryYesSearch keyword
filterNoAdditional facet:value filters, repeat the param for multiple; facet must be one of: benefits, ingredientpreferences, colorfamily, formulation, size, shoppingpreferences, agerange, skintype, finish, skinconcerns, coverage, hairtype, hairconcerns, hairtexture
is_newNoWhen true, filters to products flagged New
sort_byNoSort order, defaults to featured
page_sizeNoResults per page, 1 to 100, defaults to 60
price_maxNoMaximum price in whole dollars; must be set together with price_min
price_minNoMinimum price in whole dollars; must be set together with price_max
rating_minNoMinimum star rating, 1 to 4

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.17.5
    • addedInput schema / properties / brand / items
      Added value: +{
+  "type": "string"
+}
    • addedInput schema / properties / filter / items
      Added value: +{
+  "type": "string"
+}
    • addedInput schema / properties / sort_by / enum
      Added value: +[
+  "featured",
+  "top_rated",
+  "new",
+  "best_selling",
+  "price_low_to_high",
+  "price_high_to_low"
+]
  2. Addedv1.14.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does so well: it discloses the non-obvious fallback behavior (nonsense keyword yields an unrelated result set, never empty) and that one-sided price ranges are rejected rather than passed through, plus OR/AND facet combination semantics. It omits auth/rate-limit/pagination-limit behavior, which keeps it from a 5.

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?

Front-loaded with the purpose and return shape before the edge-case caveats, and every sentence contributes distinct information. Sentences are long and somewhat run-on (the price and facet sentences pack multiple clauses), but nothing is wasted.

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 10-parameter, no-annotation, no-output-schema tool, the description covers purpose, return contents, and the key behavioral pitfalls an agent must know to interpret results. Remaining gaps (auth requirements, maximum page, rate limits) are minor and not critical to correct invocation.

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 schema already documents all 10 parameters including the OR'd brand/filter semantics and the 'must be set together' price constraint. The description's main added value is the rationale (upstream silently ignores one-sided ranges), but most parameter meaning is a restatement, so the 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?

States a specific verb+resource ('Sephora product search ... searches Sephora's product catalog by keyword') and adds scope detail (real page-based pagination, returns brand/pricing/rating/review count). It is clearly distinct from sephora_product (detail) or sephora_suggest, but it never names a sibling to route the agent explicitly, so it stops 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?

The keyword-search framing implies when to use it, and it gives useful operational constraints (price_min/price_max together, multi-value brand/filter). However there is no explicit when-not-to-use guidance and no named alternative (e.g., sephora_suggest for autocomplete or sephora_product for a single item), leaving routing to inference.

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

Deploy Server

Other Tools