Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Get Hugging Face dataset viewer

hugging_face_datasets_viewer_get
Read-onlyIdempotent

Retrieve what a Hugging Face dataset viewer exposes for a repository by owner and name, enabling inspection of dataset structure and previews without downloading files.

Instructions

Get what a Hugging Face dataset viewer can show. Requires owner and name.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "owner": "<owner>",
      "name": "<name>",
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "hugging_face_datasets_viewer_get"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesRequired. Repository name, without the owner.
ownerYesRequired. Owner of the repository: a user or organization name.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

C2.5/5.0
Behavior2/5

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

Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, so the safety profile is covered. The description adds nothing beyond that: it does not say what the call returns, whether it fails for datasets without a configured viewer, or how errors appear — the kind of context that matters for an open-world remote lookup.

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?

Two short sentences, front-loaded and free of padding, but the second sentence duplicates information already encoded in the required-fields list of the schema. Brevity here comes at the cost of substance rather than from efficient editing.

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

Completeness2/5

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

There is no output schema, so the description carries the burden of explaining what a 'viewer' result contains, and it does not. For a tool whose whole value is returning viewer capability information, the definition leaves the agent unable to predict the response shape or recognize a negative result.

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 every parameter including context, llm_model, and conversation_id is documented in the schema itself. The description's mention of owner and name merely echoes required fields and adds no syntax, format, or constraint meaning beyond the schema.

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

Purpose3/5

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

The description names the resource ('Hugging Face dataset viewer') but the verb phrase 'Get what ... can show' is vague about what is actually retrieved (configs, splits, column info, viewer status). It gives no differentiation from close siblings such as hugging_face_datasets_get, hugging_face_datasets_rows_list, or hugging_face_datasets_statistics_get, so an agent must guess which one returns viewer metadata.

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

Usage Guidelines2/5

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

The only guidance is 'Requires `owner` and `name`', which restates schema requirements rather than telling the agent when to choose this tool over alternatives. There is no statement of when the viewer endpoint is the right call versus fetching dataset metadata or rows.

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