Skip to main content
Glama
Sign In

Feegate AI Agent data marketplace catalog & platform metrics

by org.feegate
OverviewDiscussionsAdmin

hugging-face.hf_model_ecosystem_digest

Read-onlyIdempotent

Ask "which open-weight models are most downloaded" — free: dataset meta (record count, fields, snapshot time, SHA-256) plus the first 3 sample records. ｜ 免费档：Hugging Face 开源模型生态索引 的 meta 与前 3 条样本，用于确认字段口径与数据新鲜度；45,471 个开源模型（下载量、点赞、任务类型、框架、许可证标签） 的全量走 export 付费档。

[zh] 供应方资产「Hugging Face 开源模型生态索引」免费（每日限额按调用方计）。 入参：无。 [en] Vendor asset "Hugging Face 开源模型生态索引". Free (daily per-caller quota). Args: none. 付款/支付头在 MCP 请求头里带（X-Payment / X-Payment-Tx / Authorization: Bearer fg_…），不要放进参数。

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "hugging-face.hf_model_ecosystem_digest"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Added

TDQS

A3.9/5.0
Behavior4/5

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

With annotations already covering read-only, idempotent, and non-destructive, the description adds real operational context: a daily per-caller quota, and the requirement that payment credentials travel in MCP request headers (X-Payment / X-Payment-Tx / Bearer fg_…) rather than in arguments. It stops short of quantifying the quota or describing the response envelope in detail, but the auth and billing mechanics are a genuine addition.

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?

The free-tier preview fact is front-loaded well, but the body is a bilingual mirror that repeats the same vendor, quota, and no-argument statements in Chinese and English, plus a full-width pipe separator and a marketing-style framing question. The useful content could be stated in roughly half the space.

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?

There is no output schema, so the description carries the burden of describing returns — and it does, listing meta components (record count, fields, snapshot time, SHA-256) and the 3 sample records, plus the dataset's field semantics. Combined with the disclosed auth and quota mechanics, an agent has enough to call it correctly; only the absence of any concrete example of a returned record leaves a small gap.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

There are zero parameters, which is the baseline-4 case. The description confirms 'Args: none', consistent with the empty schema, and adds nothing contradictory, though that restatement adds no new meaning beyond 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?

The description identifies the resource concretely — an index of 45,471 open-weight Hugging Face models with download counts, likes, task type, framework, and license tags — and states exactly what this tool returns: dataset meta (record count, fields, snapshot time, SHA-256) plus the first 3 sample records. It explicitly contrasts that with the full-data path (export tier). The opening framing ('which open-weight models are most downloaded') slightly oversells what a 3-record sample can answer, which keeps it short of a 5.

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?

It states the tier condition clearly: use this free digest to confirm field definitions and data freshness, and go to the export paid tier for the full dataset. It also discloses the per-caller daily quota. It does not address the sibling search tool, so the routing guidance is good but not exhaustive.

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

All Feegate AI Agent data marketplace catalog & platform metrics toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources