Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

cvs_search

Search CVS.com's OTC and non-prescription product catalog by keyword, returning product listings with prices, images, and filter facets to refine results.

Instructions

Search CVS OTC products by keyword. Performs a keyword search across CVS.com's non-prescription retail/OTC catalog and returns one page of results: products with title, brand, image, current/original price, and sponsored/featured/new-product flags; the total result count; and the facets (brand, color, size, price range, and other attributes, each with its selectable values and result counts) available to filter the results further. Covers the non-prescription retail catalog only. q is the search keyword or phrase, required. page is a 1-indexed page number (default 1). sort is an optional result order matching cvs-category's own Sort By values. CVS.com is only available from US and US-territory locations; a request served from an unsupported region returns an upstream error rather than an empty result.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qYesSearch keyword or phrase
pageNo1-indexed page number, default 1
sortNoResult sort order, default relevance. One of pa (Price Low to High), pd (Price High to Low), tr (Top Rated), rc (Most Reviewed), az (Name A-Z), za (Name Z-A)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.5
    • addedInput schema / properties / sort / enum
      Added value: +[
+  "pa",
+  "pd",
+  "tr",
+  "rc",
+  "az",
+  "za"
+]
  2. Addedv1.16.2

TDQS

A4.1/5.0
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 well: it discloses the return payload (products, prices, flags, total count, facets), says it returns only one page, and warns that unsupported regions produce an upstream error rather than an empty result. Auth and rate limits remain unstated, but this is above average for a read tool.

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-loads the core purpose and return shape, then closes with the region caveat. It is a single dense paragraph that is long but nearly every clause carries information; a slight trim of the return-field enumeration would tighten it.

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?

No output schema or annotations exist, so the description must cover behavior itself, and it does: return fields, single-page pagination, facets, and the error-mode for unsupported regions. Auth requirements and whether other pages must be fetched explicitly are the only notable omissions.

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 q, page, and the sort enum with its six values. The description restates these and adds only that sort values mirror cvs-category's Sort By list, which is marginal added value over the enum description.

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 ('Search CVS OTC products by keyword') plus an explicit scope boundary ('non-prescription retail/OTC catalog'). It references the sibling cvs-category when explaining the sort parameter, giving the agent enough to place it in the cvs_* family.

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?

Clearly frames when this tool applies (keyword search over the OTC catalog) and excludes prescription items, but never explicitly routes the agent to alternatives like cvs_category or cvs_brands for non-keyword browsing. The regional availability note is useful context rather than usage guidance.

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