Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

datasets_steam_reviews_search

Search the steam-reviews dataset. Searches the stored Steam review corpus (the most-helpful reviews per game; one document per appid × recommendation).

Instructions

Search the steam-reviews dataset. Searches the stored Steam review corpus (the most-helpful reviews per game; one document per appid × recommendation). Full-text q over the review body, filter by app_id, language, or voted_up (positive/negative). Sort enum: votes_desc (most-helpful first, default), weighted_desc, date_desc. Billing: this search costs 1 credit per record returned, with a minimum of 2 (an empty result costs 2, a full page of 100 costs 100).

Input Schema

NameRequiredDescriptionDefault
qNoFull-text query over the review body, max 256 characters
pageNoPage number, defaults to 1
sortNoSort enum: votes_desc, weighted_desc, date_desc
app_idNoExact Steam app id filter
languageNoReview language filter (e.g. english, schinese)
voted_upNoRecommendation filter: true (positive) or false (negative)
page_sizeNoPage size, defaults to 20 and maxes at 100; page * page_size must be <= 10000

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.17.5
    • addedInput schema / properties / sort / enum
      Added value: +[
+  "votes_desc",
+  "weighted_desc",
+  "date_desc"
+]
  2. Addedv1.5.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden, and it delivers the most important non-obvious trait: the billing model (1 credit per record, minimum 2, empty result still costs 2). It also discloses the corpus semantics (most-helpful-per-game, one doc per appid × recommendation). It omits auth/permission requirements and freshness/rate-limit details, but the cost disclosure is genuinely valuable context absent from the schema.

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 and corpus definition, then filters, sort, and cost in descending priority. Slightly redundant opening ('Search the steam-reviews dataset. Searches the stored Steam review corpus...'), but every remaining sentence is information-dense and earns its place.

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?

No output schema or annotations exist, so the description should stand in for both; it covers corpus nature, queryable fields, sort options, and cost, and its 'one document per appid × recommendation' line hints at the returned shape. It stops short of describing the actual returned fields or the 10000 pagination ceiling that lives only in the schema, leaving minor gaps for a 7-parameter tool.

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 schema already documents all seven parameters; the baseline is 3. The description adds only marginal meaning beyond the schema, clarifying that `votes_desc` is 'most-helpful first, default' while leaving `weighted_desc` and `date_desc` unexplained, and restating the `voted_up` positive/negative mapping already present in the schema.

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 and resource ('Search the steam-reviews dataset') and characterizes the corpus ('most-helpful reviews per game; one document per appid × recommendation'), which implicitly distinguishes it from the live `steam_reviews` and catalog-oriented `datasets_steam_games_search` siblings. It does not name those siblings explicitly, so an agent must infer the boundary, but the resource is unambiguous.

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?

The description enumerates what you can do (full-text `q` over the review body, filter by `app_id`/`language`/`voted_up`, choose a sort), which implies usage. However it gives no explicit when-to-use or when-not guidance and never routes the agent to an alternative such as `steam_reviews` for live data, leaving the sibling selection to inference.

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