Skip to main content
Glama
taiwan-stock-mcp

taiwan-stock-mcp

by hulan-bebe

scan_market

Rank Taiwan end-of-day common stocks by percentage gain/loss or TWD turnover, filtered by market and minimum price, to identify top movers or high-turnover shares.

Instructions

Rank end-of-day common stocks by percentage gain/loss or TWD turnover.

Four-digit numeric codes excluding prefix 00 only; excludes ETFs and warrants. min_price is the inclusive TWD close floor. top_n is capped at 100. Volume is shares.

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": "scan_market"
  }
}

Input Schema

NameRequiredDescriptionDefault
top_nNoPositive number of rows to return; scan caps at 100
marketNoMarket scopeall
sort_byNoRank by gain/loss percent or TWD turnovergainers
min_priceNoInclusive minimum closing price in TWD

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations at all, the description still discloses the important behavioral traits: the data is end-of-day rather than intraday, the tradable universe excludes ETFs and warrants and prefix-00 codes, top_n is hard-capped at 100, and turnover volume is in shares. It omits anything about latency, auth, or rate limits, but the operational constraints it does give are substantive.

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?

Four short lines, front-loaded with the core ranking action before the qualifying scopes. It is a bit telegraphic ('Volume is shares.' as a dangling fragment), which costs some readability, but no sentence is wasted.

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?

For a 4-parameter, zero-required scan tool with an output schema covering return values, the description does the necessary work: it pins down universe, data freshness, and the result cap. Only the market enum's scope behavior (all/twse/tpex) is left entirely to the schema, which is a minor gap.

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 schema already documents all four parameters including the enums and defaults. The description restates min_price and the top_n cap rather than adding to them; only 'Volume is shares' adds a unit that the schema's turnover description omits. Baseline 3 is appropriate.

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?

States a specific verb and resource: 'Rank end-of-day common stocks by percentage gain/loss or TWD turnover.' The scope (EOD common stocks, four-digit codes, no ETFs/warrants) makes it distinguishable from get_quote (single quote) and screen_valuation (valuation screening) in practice, though no sibling is named explicitly.

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?

Gives universe constraints ('Four-digit numeric codes excluding prefix 00 only; excludes ETFs and warrants') that implicitly define when the tool applies, but never says when to prefer it over screen_valuation or get_quote, nor any exclusions or preconditions. Usage is inferable rather than stated.

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