Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

swiggy_search

Find nearby Swiggy restaurants by location, search dishes or cuisines, browse curated collections, and retrieve ratings, delivery times, costs, and offers.

Instructions

Search Swiggy restaurants near a location. Returns restaurants delivering to a latitude/longitude, optionally filtered by a keyword or browsed within a curated collection. With no query and no collection_id this browses the nearby-restaurant listing; with a query it runs a keyword search across restaurant names, cuisines, and dishes; with a collection_id (from /swiggy/collections) it browses restaurants within that curated collection. query and collection_id are mutually exclusive. Keyword search has two result tabs, selected with tab: dish (the default) returns restaurants that serve a matching dish, each with the matching dishes, their prices, and Swiggy's own per-dish rating where it has one, in a dishes array; restaurant returns restaurants whose own name or cuisine matches, a wider set with no dishes. tab, veg, min_rating and offers are only valid together with query. sort works with either query (relevance, delivery_time, rating) or collection_id (those three plus cost_low_to_high and cost_high_to_low), and is rejected on a plain nearby browse. Each restaurant carries its id (the value the restaurant and menu endpoints take), name, cuisines, cost for two, rating, delivery time, open/closed status, a hero image, and, where one is shown, an external_rating block with the third-party aggregate score, count, and source. Where the result card advertises a promotion it also carries offers, the same title/description/tag shape /swiggy/restaurant returns (a listing card never carries a coupon code, and a card showing both a discount and a separate free-delivery benefit returns them as two entries). is_promoted is present and true only for a result Swiggy itself labels a sponsored placement rather than an organic one. unavailable_message is present only when Swiggy says the restaurant cannot currently be ordered from and carries its own reason; it is not the inverse of is_open, since Swiggy reports a restaurant as open while still refusing orders for the requested location. A plain nearby browse also returns is_serviceable, which says whether Swiggy delivers to the requested coordinates at all: false means the coordinates are outside Swiggy's delivery coverage, so the empty restaurants list is a coverage answer rather than a no-matches answer, while an empty list without the field means no matches in a served area. It is omitted on keyword search and on a collection_id browse, neither of which carries Swiggy's own coverage marker.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tabNoWhich keyword-search result tab to read: dish (default, restaurants serving a matching dish, each with a dishes array) or restaurant (restaurants whose own name/cuisine matches). Only valid together with query.
vegNoOnly return vegetarian results: veg dishes on tab=dish, pure-veg restaurants on tab=restaurant. Only valid together with query.
sortNoOptional sort order. With query: relevance, delivery_time, rating. With collection_id: those three plus cost_low_to_high and cost_high_to_low. Not valid on a plain nearby browse.
queryNoOptional keyword to search restaurants and dishes by, at least 2 characters. Mutually exclusive with collection_id.
offersNoOnly return restaurants currently running an offer. Only valid together with query.
offsetNoOpaque pagination cursor from a prior response's next_offset (not meaningful when query is set)
latitudeYesSearch center latitude
longitudeYesSearch center longitude
min_ratingNoOnly return restaurants rated at or above this score (0-5). Only valid together with query.
collection_idNoOptional curated collection id from /swiggy/collections's id field. Browses restaurants within that collection instead of the plain nearby listing. Mutually exclusive with query.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.16.2

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden, and it goes well beyond a basic summary. It discloses nuanced result semantics such as unavailable_message not being the inverse of is_open, is_serviceable indicating coverage vs. no-matches, is_promoted indicating sponsored placement, offer shape differences, and valid sort contexts. This is unusually detailed behavioral disclosure.

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?

The description is long, but every sentence earns its place given the three modes, conditional parameter rules, and non-obvious result-field semantics. It is front-loaded with purpose and mode selection before output details. It could be slightly easier to scan with bullets or headings, but it is not padded.

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?

Given high complexity, no annotations, and no output schema, the description is remarkably complete. It covers all three modes, parameter validity, sort values, per-restaurant fields, offer/promotion structure, sponsored markers, unavailable_message, is_serviceable coverage interpretation, and empty-list meaning. An agent has the information needed to call and interpret this tool correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Although the schema already documents all 10 parameters, the description adds meaningful semantic constraints beyond it: valid combinations per mode, default tab behavior, allowed sort values per mode, collection_id provenance, and mutual exclusion. This substantially helps an agent pick correct parameter combinations in ways the schema alone does not convey.

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 Swiggy restaurants near a location'—and immediately clarifies the tool returns restaurants delivering to a latitude/longitude. It then explicitly distinguishes three modes (nearby browse, keyword search, collection browse), making it easy to tell what this endpoint does and how it relates to the restaurant/menu endpoints.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives explicit mode-selection rules: no query and no collection_id browses nearby restaurants, a query runs keyword search, and a collection_id browses a curated collection. It also states exclusions—query and collection_id are mutually exclusive, tab/veg/min_rating/offers are only valid with query, and sort is rejected on a plain nearby browse—so an agent knows exactly when each call shape is legal.

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

Install Server

Other Tools