Skip to main content
Glama
bibo242

haraj-mcp

by bibo242

search

Read-onlyIdempotent

Find Haraj.com.sa classifieds by keyword, filtering results by city, tag, date, media type, or location. Returns matching posts with pagination.

Instructions

Search haraj by keyword. Required: keyword. Optional: cities (list), city, tag, tags (list), page, limit, only_with_image (default true), only_with_video (default false), hide_show_rooms (default false), order_by_post_id (default false), during_date ('1days'|'3days'|'1week'|'1months'), near ('@lat,lon' e.g. '@26.4336,50.1116'), full (default false = compact). Returns {keyword, count, has_next_page, view_options, posts}.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagNoRestrict the search to a single Arabic tag.
cityNoSingle Arabic region name to filter by.
fullNoReturn full Post objects instead of compact summaries.
nearNoGeohash location filter like '@26.4336,50.1116'.
pageNoZero-based page index.
tagsNoRestrict the search to a list of Arabic tags.
limitNoNumber of posts to return (clamped to 1-100).
citiesNoList of Arabic region names to filter by.
keywordYesSearch keyword (Arabic or English), e.g. 'RTX 4090' or 'شاشة'.
during_dateNoTime window: '1days', '3days', '1week', or '1months'.
hide_show_roomsNoIf true, hides dealer posts (real-estate filter).
only_with_imageNoOnly return posts that have at least one image.
only_with_videoNoOnly return posts that have a video.
order_by_post_idNoOrder results by post id instead of relevance/date.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changedv0.5.0
    • addedInput schema / properties / cities / description
      Added value: +"List of Arabic region names to filter by."
    • addedInput schema / properties / city / description
      Added value: +"Single Arabic region name to filter by."
    • addedInput schema / properties / during_date / description
      Added value: +"Time window: '1days', '3days', '1week', or '1months'."
    • addedInput schema / properties / full / description
      Added value: +"Return full Post objects instead of compact summaries."
    • addedInput schema / properties / hide_show_rooms / description
      Added value: +"If true, hides dealer posts (real-estate filter)."
    • addedInput schema / properties / keyword / description
      Added value: +"Search keyword (Arabic or English), e.g. 'RTX 4090' or 'شاشة'."
    • addedInput schema / properties / limit / description
      Added value: +"Number of posts to return (clamped to 1-100)."
    • addedInput schema / properties / near / description
      Added value: +"Geohash location filter like '@26.4336,50.1116'."
    • addedInput schema / properties / only_with_image / description
      Added value: +"Only return posts that have at least one image."
    • addedInput schema / properties / only_with_video / description
      Added value: +"Only return posts that have a video."
    • addedInput schema / properties / order_by_post_id / description
      Added value: +"Order results by post id instead of relevance/date."
    • addedInput schema / properties / page / description
      Added value: +"Zero-based page index."
    • addedInput schema / properties / tag / description
      Added value: +"Restrict the search to a single Arabic tag."
    • addedInput schema / properties / tags / description
      Added value: +"Restrict the search to a list of Arabic tags."
  2. First observedv0.3.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already declare this as a safe, read-only, idempotent, open-world read. The description adds material context beyond that: the compact-vs-full return mode and the exact return envelope ({keyword, count, has_next_page, view_options, posts}), which tells the agent what to expect back. It still omits pagination semantics (page/count interaction) and rate-limit behavior.

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

Conciseness3/5

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

Front-loads the purpose well and stays compact, but then enumerates all 14 parameters with their defaults, which duplicates a schema that already carries 100% description coverage. That parameter dump is largely non-earning text where a pointer to the schema would have sufficed.

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 tool with 14 parameters, no output schema, and no enum declarations, the description supplies the missing return shape and confirms default behaviors, which is enough for an agent to call it correctly. Minor gaps remain around pagination/has_next_page semantics and relative ordering when order_by_post_id is false.

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%, so the parameters are already fully documented by the schema, including defaults, ranges (limit 1-100), and the during_date and near formats. The description largely restates those same parameters and formats, adding no new semantics, so the baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource ('Search haraj by keyword') and enumerates the filterable dimensions, so an agent immediately knows this is the keyword-driven post search. It does not, however, distinguish itself from siblings like search_suggest or trending_keywords, which also touch search/query concepts.

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

Usage Guidelines3/5

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

Usage is implied by the required/optional split and the parameter list, but there is no explicit when-to-use guidance, no exclusions, and no reference to alternative tools such as search_suggest for query discovery or fetch_feed for browsing. An agent must infer context from the schema alone.

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