Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

jumia_search

Search a Jumia country storefront by keyword to retrieve product cards with prices, discounts, ratings, brands, and pagination flags. Retry on 503 responses from anti-bot challenges.

Instructions

Search Jumia products. Searches a Jumia country storefront by keyword and returns one page of product cards with price in the storefront's currency, original price and discount, rating, brand, categories and badges, plus the upstream total_count and a has_next flag. Jumia serves at most 50 pages. A search with no matches returns an empty products list. Jumia sits behind an anti-bot challenge that clears on only some connections, so a call can take up to about 50 seconds and may return 503; retry it. country is required (there is no default storefront); see jumia-countries.

Input Schema

NameRequiredDescriptionDefault
qYesProduct search keyword
pageNo1-based result page, 1 to 50
countryYesJumia country storefront

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.16

TDQS

A4.4/5.0
Behavior5/5

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

No annotations exist, so the description carries the full burden and does so well: it discloses the 50-page cap, the empty-result behavior, the anti-bot challenge causing ~50s latency and possible 503s with a retry instruction, plus the exact response shape (price in local currency, original price/discount, rating, brand, categories, badges, total_count, has_next).

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?

Front-loaded with purpose, then return shape, then limits, then failure mode and retry guidance, then the required-parameter note. Dense but every sentence carries operational value; only the return-shape enumeration borders on verbose.

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 a search tool with no output schema and no annotations, this covers everything an agent needs: valid inputs, join to jumia-countries, page limits, empty-result semantics, output fields, and the slow-flaky-retry behavior that would otherwise cause an agent to abort or mis-handle a 503.

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 coverage is 100%, so both params are already documented in the schema. The description adds the constraint that country has no default and must be sourced from jumia-countries, but says nothing extra about page or q semantics. Baseline 3 is appropriate given the schema does the heavy lifting.

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 (Jumia products), and immediately scopes it: one page of product cards from a country storefront. Siblings like jumia_product, jumia_category, and jumia_reviews cover different resources and the description's 'by keyword' framing makes the distinction clear.

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?

Explains that country is required with no default and points to jumia-countries for valid values, but doesn't explicitly say when to prefer jumia_category or jumia_product instead. Usage is strongly implied rather than exhaustively enumerated.

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