Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

justeat_search

Search Just Eat restaurants by UK postcode and retrieve the complete listing with ratings, delivery time, and open-now status.

Instructions

Search Just Eat restaurants near a UK postcode. Returns Just Eat's full restaurant listing for a UK postcode -- every restaurant the site's own area page carries, ordered as Just Eat's default "best match" sort presents them (or by sort_by, if set), not a curated subset. Each restaurant carries its unique_name (the value the restaurant and menu endpoints take), name, image, rating, delivery time window, and open-now status. A postcode with no coverage returns an empty list rather than an error.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoRestaurants to return, clamped to 100 (default 20)
filterNoRepeatable. Just Eat's own area-page filter slugs (e.g. open_now, or a cuisine tile's slug), passed through as-is and OR'd together. Also reaches non-restaurant categories -- groceries, alcohol, pharmacy, electronics, and more -- via the same mechanism, e.g. filter=groceries. The valid slug set is specific to the postcode you are searching -- call /justeat/search/filters with the same postcode for the current, complete, location-scoped list with live result counts. An unrecognized slug narrows to a smaller or empty result rather than erroring.
sort_byNoResult order, matching the area page's own Sort by control. Default best_match.
postcodeYesUK postcode to search near

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv1.17.5
    • changedInput schema / properties / filter / description
      Previous value: -"Repeatable. Just Eat's own area-page filter slugs (e.g. open_now, or a cuisine tile's slug), passed through as-is and OR'd together. Also reaches non-restaurant categories -- groceries, alcohol, pharmacy, electronics, and more -- via the same mechanism, e.g. filter=groceries. See the endpoint markdown for the confirmed slug list. An unrecognized slug narrows to a smaller or empty result rather than erroring."New value: +"Repeatable. Just Eat's own area-page filter slugs (e.g. open_now, or a cuisine tile's slug), passed through as-is and OR'd together. Also reaches non-restaurant categories -- groceries, alcohol, pharmacy, electronics, and more -- via the same mechanism, e.g. filter=groceries. The valid slug set is specific to the postcode you are searching -- call /justeat/search/filters with the same postcode for the current, complete, location-scoped list with live result counts. An unrecognized slug narrows to a smaller or empty result rather than erroring."
    • addedInput schema / properties / filter / items
      Added value: +{
      +  "type": "string"
      +}
    • addedInput schema / properties / sort_by / enum
      Added value: +[
      +  "best_match",
      +  "review_rating",
      +  "distance",
      +  "delivery_time",
      +  "minimum_order_value",
      +  "delivery_fee"
      +]
  2. Addedv1.16.2

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so thoroughly. It discloses default best-match ordering, the effect of sort_by, the non-curated full-listing behavior, the exact fields returned, filter pass-through semantics, unknown-slug behavior, and empty-list rather than error for uncovered postcodes.

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?

The definition is front-loaded with a clear purpose and every subsequent clause earns its place: full-listing scope, ordering rules, returned fields, filter mechanics, and an edge-case guarantee. There is no filler or repetition beyond what is needed for precision.

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?

There is no output schema, yet the description names the key fields returned and explains behavioral edge cases such as empty results, filter slug validity, and where to fetch valid filters. Combined with a fully documented input schema, an agent has everything needed to invoke the tool correctly.

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 filter slugs are OR'd together, can reach non-restaurant categories like groceries, are postcode-specific, and that unrecognized slugs narrow results instead of erroring. It also clarifies the default sort behavior.

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 opening sentence names the verb ('Search'), the resource ('Just Eat restaurants'), and the scope ('near a UK postcode'). It then sharpens the definition by saying the tool returns the site's full restaurant listing, not a curated subset, which distinguishes it from other Just Eat endpoints.

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?

The description tells agents to call /justeat/search/filters for location-scoped filter slugs and explains that each result's unique_name feeds the restaurant and menu endpoints. It doesn't explicitly state when to prefer this tool over sibling search-related tools, but the guidance is strong enough to route an agent correctly.

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