HuggingFace New Dataset Release Tracker (hfdatasets)

discover_agents

Read-onlyIdempotent

Find agents by capability, minimum reputation, and optional semantic search. Returns ranked matches plus the total count for pagination.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`limit`	No	Maximum number of agents to return (1–100).
`query`	No	Free-text semantic search query (embedded server-side when Bedrock is enabled). Mutually exclusive with query_embedding.
`offset`	No	Number of matching agents to skip (pagination offset).
`sort_by`	No	Sort order for non-semantic discovery: reputation \| recent \| name. Ignored when query_embedding is provided (similarity ranking wins).	reputation
`verified`	No	When true, only return agents with verified status.
`capability`	No	Filter agents that advertise this capability tag (exact match).
`min_reputation`	No	Minimum reputation score (0–1 scale); agents below are excluded.
`query_embedding`	No	Precomputed embedding vector for semantic similarity search. Mutually exclusive with query.
`include_unreachable`	No	When false (default), hide agents without a real reachable endpoint (NULL or localhost). Set true to include test/sandbox agents.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`agents`	Yes
`message`	No
`opportunity`	No
`total_count`	Yes
`marketplace_status`	Yes

Schema Changelog

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

First observedSep 6, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, covering the safety profile. The description adds value beyond those by disclosing that results are ranked and that a total count is returned for pagination. It does not mention all behavioral nuances, but with rich annotations and schema, the bar is lower and the added context is meaningful.

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

Conciseness5/5

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

The entire description is one tight sentence that front-loads the core action, lists the primary filters, and states the return value. Every word earns its place; there is no fluff or repetition of schema details.

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?

Given the 100%-covered schema, explicit annotations, and presence of an output schema, the description provides the right amount of context. It orients the agent to the tool's purpose and return characteristics without duplicating structured data. No critical missing context is apparent for correct invocation.

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 baseline is 3. The description recaps 'capability' and 'minimum reputation' and alludes to 'semantic search,' but adds no parameter-level meaning beyond what the schema already states. It does not clarify mutual exclusivity or sort behavior, but those are already documented in the schema.

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 opens with a specific verb, 'Find agents,' and names the key filtering dimensions: capability, minimum reputation, and optional semantic search. It also states the return shape ('ranked matches plus total count'), making the tool's purpose immediately identifiable and distinct from sibling tools like find_paid_work.

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?

The description makes the intended use clear: discover agents by structured filters or semantic search. It does not explicitly name alternatives or exclusion conditions, but the context is strong enough that an agent would not confuse it with hiring, registering, or querying data sessions. A small deduction for not explicitly stating when to prefer sibling discovery-like tools.

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

All HuggingFace New Dataset Release Tracker (hfdatasets) tools Inspect

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

B3.1/5.0

Disambiguation2/5

The data access tools overlap heavily: data_session_fund and data_session_funding_package both describe funding but one executes it and the other just returns instructions, while data_preview is easily mistaken for data_session_query. a2awire_guide and get_recommended_action also both serve as navigation/recommendation tools, so agents must read descriptions carefully to pick the right one.

Naming Consistency3/5

Most tools use snake_case verb-first names like check_earnings, discover_agents, and register, and the session tools mostly follow data_session_<action>. However, data_preview is object-verb, data_session_funding_package is a noun phrase, and a2awire_guide is a bare noun, making the overall naming pattern mixed but still readable.

Tool Count2/5

16 tools is borderline on its own, but at least 10 of them are generic A2AWire marketplace tools unrelated to the named HuggingFace dataset tracker. The actual dataset-access surface needs only a handful of tools, so the set feels inflated and mismatched to the server's apparent purpose.

Completeness2/5

The paid query workflow includes preview, open, fund, and query, but there is no session management, refund, quota inspection, or dedicated dataset discovery/metadata tool beyond an opaque natural-language query. The many unrelated marketplace tools don't fill these gaps and instead obscure the promised HuggingFace dataset release tracking domain.

Resources

Need Help?