Skip to main content
Glama

Huggingface

by io.github.pipeworx-io

Search Datasets

search_datasets
Read-onlyIdempotent

Search Hugging Face Hub datasets with filters for author, language, and task_categories; sort by downloads, likes, or lastModified; returns dataset id, downloads, likes, and tags.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fullNo
sortNo
limitNo
authorNo
searchNo
languageNoISO language code, e.g. "fr"
directionNo
task_categoriesNoComma-separated task categories, e.g. "question-answering"

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • addedInput schema / properties / language / description
      Added value: +"ISO language code, e.g. \"fr\""
    • changedInput schema / properties / task_categories / description
      Previous value: -"Comma-separated task categories"New value: +"Comma-separated task categories, e.g. \"question-answering\""
  2. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "limit": 20,
+    "search": "imagenet"
+  },
+  {
+    "author": "wikipedia",
+    "language": "en",
+    "limit": 15,
+    "sort": "likes",
+    "task_categories": "text-classification"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "description": "List of datasets matching search criteria",
+  "type": "object"
+}
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint, and destructiveHint false, making the safety profile clear. The description adds value by specifying the return fields (dataset id, downloads, likes, tags) and the supported sort options, which are not covered by 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?

The description is a single sentence that efficiently conveys the core functionality. It is well-structured and front-loads the key information, though it could be slightly more concise by omitting redundant phrasing.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Despite having an output schema, the description omits several important aspects: it does not mention default values (e.g., limit), the 'direction' parameter, or the 'full' boolean flag. For a tool with 8 parameters and no required ones, more details are needed to help the agent form a precise request.

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 only 25%, with only 'language' and 'task_categories' having descriptions. The description clarifies that 'author', 'language', and 'task_categories' are filters, and 'sort' can be 'downloads', 'likes', or 'lastModified', but it omits parameters like 'full', 'direction', 'limit', and 'search', leaving their semantics unclear.

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 description clearly states the tool searches Hugging Face Hub datasets with specific filters (author, language, task_categories) and sorting options, and explicitly lists the returned fields (id, downloads, likes, tags). This differentiates it from sibling tools that search models or spaces.

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?

While the description mentions filters and sorting, it provides no guidance on when to use this tool versus alternative search tools (e.g., search_models, search_spaces). There is no explicit 'when-to-use' or 'when-not-to-use' context.

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

All Huggingface toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0
Disambiguation3/5

The tool set includes many similarly-named tools, especially the 'ask_pipeworx' variants and the multiple polymarket tools, which could cause confusion. However, each tool has a detailed description specifying its unique purpose, so an agent reading carefully can distinguish them.

Naming Consistency2/5

Naming is inconsistent across the set: Huggingface tools use 'get_', 'list_', 'search_' prefixes, while Pipeworx tools use varied verbs like 'ask_pipeworx', 'bet_research', 'entity_profile', and others. There is no overall pattern or convention, making it harder to predict tool names.

Tool Count2/5

With 41 tools, the server is heavily loaded. While each tool has a distinct role, the scope combines two large domains (Huggingface and Pipeworx), leading to a tool count well above the typical 3-15 range for a focused server.

Completeness3/5

The server covers a wide range of functionalities: Huggingface model/dataset queries, Pipeworx data lookups, subscription management, and memory tools. However, it lacks write operations for Huggingface (e.g., uploading models/datasets) and some lifecycle operations, leaving noticeable gaps.

Resources