Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

wolt_search

Search Wolt restaurants and stores near any coordinates, with optional keyword or category filters, and get ratings, delivery estimates, and coverage status.

Instructions

Search Wolt restaurants and stores near a coordinate. Returns restaurants and stores near a coordinate, optionally filtered by a keyword or browsed by category. With none of those, this reads Wolt's own plain location browse; with a query it uses Wolt's own keyword search across restaurant/store names, dishes, and cuisines; with a category it browses Wolt's own per-category listing (the same page a homepage cuisine tile links to) -- call /wolt/search/filters for the current, complete, location-scoped list of valid category values. category and query cannot be combined. A keyword search additionally accepts sort, product_line, and open_now; those three apply to keyword search only and return a 400 without query. Each result carries its slug (the value the restaurant and menu endpoints take), name, address, coordinates, tags, price range, rating, and delivery estimate; the two browse modes additionally carry each venue's own category ids. The response also carries is_serviceable, which says whether Wolt delivers to the requested coordinates at all: false means the coordinates are outside Wolt's delivery coverage, so the empty results list is a coverage answer rather than a no-matches answer. A keyword that simply matches nothing inside a covered area returns an empty list with is_serviceable true. Call /wolt/cities for the coordinates of every city Wolt operates in.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNoOptional result ordering. Only applies together with query -- Wolt exposes sorting on its keyword search only, not on its plain browse or category listings.
limitNoMax restaurants/stores returned. Defaults to 30, maximum 100.
queryNoOptional keyword to search restaurant/store names, dishes, or cuisines by. Cannot be combined with category.
categoryNoOptional Wolt category id to browse by instead of a keyword search, e.g. pizza, sushi, vegan. Call /wolt/search/filters for the current, complete, location-scoped list of valid values. Cannot be combined with query. A value Wolt does not recognize at all returns a 404; a real category this particular market does not use returns an empty list, since the taxonomy is location-scoped and markets differ.
latitudeYesSearch center latitude
open_nowNoWhen true, restrict results to venues currently delivering. Only applies together with query.
longitudeYesSearch center longitude
product_lineNoOptional store-type filter. Only applies together with query. Which store types a market actually stocks varies by country; one absent from the searched market returns no results rather than an error.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.16.2

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full behavioral burden and delivers: is_serviceable semantics (false means outside delivery coverage, so an empty list is a coverage answer rather than a no-matches answer), the 400 error for keyword-only params used without query, the 404 vs empty-list distinction for category values, and explicit enumeration of result fields. These are exactly the behavioral traits an agent must know to interpret responses correctly.

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 densely informative, with purpose front-loaded before mode explanations and error semantics. There is minor redundancy between the opening sentence and the second sentence ('Search Wolt restaurants and stores near a coordinate' vs 'Returns restaurants and stores near a coordinate, optionally filtered...'), and the content is one dense block with no paragraph breaks, but every substantive sentence earns its place, especially given the absence of an output schema.

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 an 8-parameter, three-mode tool with no output schema and no annotations, this description is essentially complete: all modes and their conditional parameter applicability are covered, response contents are enumerated (slug, name, address, coordinates, tags, price range, rating, delivery estimate), error/coverage semantics are explained, and the agent is routed to sibling tools for categories and cities. Any residual gaps are minor.

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. The description adds real value beyond the schema by explaining that query searches 'restaurant/store names, dishes, and cuisines', that keyword-only params 'return a 400 without query', and that browse modes additionally carry each venue's category ids. Some content is redundant with the schema (category 404/empty-list semantics, the /wolt/search/filters pointer), which keeps this at 4 rather than 5.

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 first sentence states a specific verb ('Search'), resource ('Wolt restaurants and stores'), and scope ('near a coordinate'). The description then precisely enumerates three distinct modes (plain browse, keyword search, category browse) and cross-references sibling endpoints ('the restaurant and menu endpoints take', '/wolt/search/filters', '/wolt/cities'), making differentiation from wolt_restaurant, wolt_search_filters, and wolt_cities straightforward.

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?

The description gives explicit when-to-use guidance for all three modes, states the mutual exclusion between category and query, and warns that sort, product_line, and open_now 'return a 400 without query'. It actively routes the agent: 'call /wolt/search/filters for the current, complete, location-scoped list of valid category values' and 'Call /wolt/cities for the coordinates of every city Wolt operates in', plus the slug handoff to restaurant/menu endpoints.

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