Crawlora MCP

Official

Overview Schema Source Related Servers Discussions Admin

petsmart_search

Search PetSmart products by keyword, category, brand, price, rating, or filters, and sort/page results to find product details and availability.

Instructions

Search PetSmart products. Returns one page of PetSmart products from its catalog of about 20,000, optionally narrowed by keyword, category, brand, price range, minimum rating or any catalog filter, in six orderings (relevance, price_asc, price_desc, best_sellers, top_rated, new_arrivals). Each product carries its SKU id, master product id, name, brand, price (current, list and PetSmart's display text, with the range across sizes), images, rating and review count, primary category, pets, size, variations, UPC and availability flags (available online, in stock in stores, in-store only, online only, pickup and autoship eligible). total_results and total_pages describe the whole result set; PetSmart pages no deeper than 10,000 results, so narrow the search to reach the rest. Call /petsmart/categories and /petsmart/search/filters for the valid category and filter values; an unknown category path or filter name returns a 400 rather than an empty list. Pass country=ca for the Canadian catalog.

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": "petsmart_search"
  }
}

Input Schema

Name	Required	Description
`page`	No	Optional 1-based page number. Defaults to 1.
`sort`	No	Optional ordering.
`brand`	No	Optional exact brand name. Find values with /petsmart/search/filters using facet=brand and facet_query.
`limit`	No	Optional products per page. Defaults to 24, maximum 100.
`query`	No	Optional keyword.
`filter`	No	Optional catalog filters as name:value, repeatable (for example customPet:Dog). Names and values come from /petsmart/search/filters; an unknown name returns a 400. Different names combine with AND; repeating one name combines its values with OR.
`country`	No	Optional catalog: us (default) or ca for the Canadian store, which has its own products (about 9,000), categories, filters and prices.
`category`	No	Optional category path, from /petsmart/categories' path field (for example Dog > Food > Dry Food). Includes the category's descendants. A path not in the directory returns a 400.
`max_price`	No	Optional maximum price in dollars.
`min_price`	No	Optional minimum price in dollars.
`min_rating`	No	Optional minimum average customer rating, 0 to 5.

Schema Changelog

Changes observed during successful MCP inspections.

Addedv1.17.20Nov 12, 2026

TDQS

A4.6/5.0

Behavior5/5

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

With no annotations at all, the description carries the full burden and does so well: it discloses the ~20,000-item catalog size and ~9,000 for Canada, the hard 10,000-result paging ceiling, the 400-error (rather than empty-list) behavior for unknown category paths and filter names, and the AND/OR combination semantics for filters. It also spells out payload contents and the total_results/total_pages fields, so an agent knows what a call yields and how it fails.

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?

Purpose and scope are front-loaded in the first clause, and the two most actionable warnings (400 on bad category/filter, 10,000-result cap) follow the main flow. The long enumeration of returned fields is dense but earns its place because there is no output schema to carry that information.

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?

Eleven optional parameters, all fully documented in the schema, plus a description that covers return fields, pagination limits, error behavior and the country variant — comprehensive for a search tool with no output schema and no annotations.

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 the baseline is 3, but the description adds operational meaning beyond the schema: it ties the page parameter to the 10,000-result depth ceiling and tells the agent to narrow instead of paging, and clarifies that country=ca is a genuinely separate catalog with its own categories, filters and prices. It doesn't add format specifics for min_price/min_rating beyond what the schema already states.

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?

The description opens with a specific verb and resource ("Search PetSmart products") and immediately bounds the scope: one page from a ~20,000-item catalog, narrowed by keyword, category, brand, price, rating or catalog filter, in six named orderings. This is enough to separate it from petsmart_product (single product) and petsmart_search_filters/categories without opening any 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 gives clear when-to-use context: filter to narrow, fetch valid values from /petsmart/categories and /petsmart/search/filters, use country=ca for Canada, and narrow rather than page deep because PetSmart caps at 10,000 results. What's missing is explicit routing to alternatives — it never says to use petsmart_product when you already have a SKU, and it names API endpoints rather than the sibling tools themselves.

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

Deploy Server