Crawlora MCP

datasets_doordash_stores_search

Read-only

Search the DoorDash store directory dataset for stores by keyword, country, state, city, or marketplace tag. Costs 1 credit per record returned (minimum 2), so keep page_size to what you need. Results include store identity, address, coordinates, ratings, and crawl-time availability; use this for discovery before retrieving one store's full record.

Input Schema

Name	Required	Description
`q`	No	Optional full-text search over store name, address, city, and marketplace tags, max 256 characters.
`lat`	No	Optional latitude for radius filtering or distance sort, from -90 through 90; supply together with lon.
`lon`	No	Optional longitude for radius filtering or distance sort, from -180 through 180; supply together with lat.
`tag`	No	Optional single marketplace tag filter, e.g. Pizza or Grocery. Repeat via /doordash-stores/facets?facet=tags to discover the full tag set.
`city`	No	Optional exact city filter.
`page`	No	Offset page number, 1-based, default 1; the 10000-result window applies only to offset pagination.
`sort`	No	Optional sort order. Allowed values: relevance, rating, distance, distance_asc. Relevance ranks text matches when q is supplied and otherwise sorts by store name.
`state`	No	Optional state/region code filter, e.g. CA.
`cursor`	No	Opaque continuation cursor returned as next_cursor. Use with pagination=cursor and the same filters and sort.
`country`	No	Optional ISO-3166-1 alpha-2 country filter, e.g. US, CA.
`radius_m`	No	Optional radius in meters, from 1 through 50000; requires lat and lon.
`max_price`	No	Optional maximum price range tier, inclusive.
`min_price`	No	Optional minimum price range tier, inclusive.
`page_size`	No	Page size, default 20, max 100; page times page_size must not exceed 10000.
`min_rating`	No	Optional minimum aggregate rating, from 0 through 5. Stores DoorDash reports with no rating are excluded.
`pagination`	No	Pagination mode: offset or cursor. Cursor mode uses a point-in-time snapshot and can enumerate beyond 10,000 results.
`dash_pass_only`	No	Optional flag; when true, keep only stores DoorDash marks DashPass eligible.

Output Schema

Name	Required	Description	Default
`data`	Yes	The tool result payload (shape varies per tool; see each tool's docs resource).

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 7, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Adds non-obvious behavioral facts beyond annotations: costs 1 credit per record with a minimum of 2, and warns to keep page_size minimal. readOnlyHint=true is consistent with a search. It does not mention rate limits or the 10,000-result offset cap, but page/cursor limits live in the schema, so this is solid.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, front-loaded with purpose, then cost guidance, then return fields and the discovery framing. No filler; every sentence carries information.

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 17-param search with 100% schema coverage, a full output schema, and readOnly/openWorld annotations, the description covers purpose, cost, and result shape. It omits pagination-window and cursor-vs-offset nuance, but those are documented in the schema and the sibling facets tool, so completeness is strong.

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 description coverage is 100% and each of the 17 params is fully documented in the schema, so the baseline is 3. The description mentions the filter dimensions available but adds no syntax or extra meaning beyond the schema.

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 (Search) and resource (DoorDash store directory) plus the filter dimensions (keyword, country, state, city, marketplace tag). It also explicitly distinguishes itself from the sibling retrieval tool by calling itself 'discovery before retrieving one store's full record'.

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?

Explicitly frames usage as discovery prior to fetching a single store's full record, which routes the agent correctly. It does not name the specific sibling (datasets_doordash_stores_item) or datasets_doordash_stores_nearby, so exclusion guidance is slightly less complete than ideal.

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

All Crawlora MCP tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.