出口单 chukoudan

数据集数据行

get_dataset_rows

Read-onlyIdempotent

一个数据集版本的一页数据行，与发布的一致（不指定版本时取当前版本）。 A page of the rows of one dataset version, as published (the current version when none is named). 结果仅供计算参考，不是税务、法律或投资意见；回答时请带上返回的说明和来源行。 / The result is for calculation and reference only, not tax, legal or investment advice; when you answer, pass on the returned notice and source line.

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": {
      "dataset": "<dataset>"
    },
    "name": "get_dataset_rows"
  }
}

Input Schema

Name	Required	Description
`limit`	No	一页多少行，默认 1000，最多 5000。 Rows in the page (default 1000, at most 5000).
`offset`	No	跳过的行数，默认 0。 Rows to skip (default 0).
`dataset`	Yes	数据集编号，来自 list_datasets，例如 central-parity（人民币汇率中间价）。 A dataset id from list_datasets.
`version`	No	版本号，来自 get_dataset；不填就是当前版本。 A version from get_dataset; the current one when left out.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 15, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds a genuine behavioral obligation beyond that: results are calculation-reference only, and the agent must relay the returned notice and source line when answering. It does not discuss rate limits or the cost of large pages.

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 purpose is front-loaded, but the entire text is duplicated in Chinese and English, so roughly half the content is redundant for any given reader. The disclaimer sentence is useful but sits in the primary description slot ahead of any paging guidance.

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?

With no output schema, the description does hint at return content (a notice and a source line), and it covers versioning and paging, which are the main correctness risks for this call. The only real gap is guidance on iterating pages.

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 coverage is 100%, so limit/offset bounds, defaults and the dataset/version sourcing rules are already fully documented in the schema. The description's 'current version when none is named' restates what the version parameter description already says, adding no new syntax or format guidance.

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 states a specific verb+resource ('a page of the rows of one dataset version, as published') and pins down the versioning default, so an agent knows it retrieves data rows rather than metadata. It never explicitly contrasts itself with get_dataset or list_datasets, which are only referenced indirectly via the parameter descriptions.

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?

Usage is implied: a dataset id 'from list_datasets' and a version 'from get_dataset', plus the rule that omitting version means current. There is no statement of when to choose this over get_dataset or how to page through results until exhausted beyond the offset parameter.

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

All 出口单 chukoudan tools Inspect

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

Need Help?