Skip to main content
Glama

Taiwan Daily Movers

taiwan_daily_movers
Read-onlyIdempotent

Largest gainers or losers among Taiwan Stock Exchange (TWSE) listed stocks for the latest session, ranked by percent change computed from the published close and change, with name, code, close, volume and value. ETFs, ETNs, warrants and preferred lines are excluded by default (exclude_etf). Answers "Taiwan stocks with the biggest daily gain", "largest and smallest % change among TWSE-listed stocks excluding ETFs and warrants", "today's top losers on the Taiwan Stock Exchange", "台股 漲幅排行". Main board only; only the latest published session is available.

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "limit": 5,
      "direction": "gainers"
    },
    "name": "taiwan_daily_movers"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoTrading date YYYY-MM-DD. Only the latest session is published; any other date returns found:false naming it.
limitNoHow many to return, 1-100. Default 10.
directionNogainers = largest % rise first (default); losers = largest % fall first.
exclude_etfNoLeave out ETFs, ETNs, warrants and preferred lines, ranking listed companies only. Default true.

Output Schema

NameRequiredDescriptionDefault
noteNo
foundNo
moversNo
sourceNo
messageNo
returnedNo
directionNo
data_as_ofNo
exclude_etfNo
trading_dateNo
latest_sessionNo
requested_dateNo
securities_rankedNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already cover read-only, non-destructive, idempotent and open-world, so the description's job is to add operating context, which it does: only the latest published session exists, older dates come back as found:false naming the date, rankings are derived from the published close and change, and the default exclusion of fund/warrant/preferred lines is disclosed. Return shape is not described, but an output schema exists, so that omission is acceptable.

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?

Front-loaded with the core definition, then scope constraints, then query examples. Slightly padded: the quoted example 'largest and smallest % change among TWSE-listed stocks excluding ETFs and warrants' repeats the exclusion clause stated one sentence earlier, and four example phrasings is more than needed.

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 four-parameter, all-optional read tool with full schema coverage and an output schema, the description covers universe, ranking metric, exclusions, session limitation and error behavior. The one remaining ambiguity is whether a date outside the published session returns found:false rather than an empty list, which the schema states but the description only implies.

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 all four parameters (date, limit, direction, exclude_etf) already carry their own descriptions and defaults. The description adds only the ranking basis and the exclusion rationale, largely restating what the schema's exclude_etf description already says, so baseline 3 applies.

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?

States a specific verb-less but precise operation: ranking of largest gainers/losers among TWSE-listed stocks for the latest session, with the exact metric ('ranked by percent change computed from the published close and change') and the returned fields. The universe and board ('TWSE listed', 'Main board only') distinguish it from quote, top-traded and search siblings without needing to open their schemas.

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?

Embedded example intents ('Taiwan stocks with the biggest daily gain', 'today's top losers', '台股 漲幅排行') make the triggering conditions clear, and the description states the eligibility boundary (excludes ETFs/ETNs/warrants/preferred by default) plus the restriction to the latest published session. It does not name a sibling as the alternative for volume- or value-based rankings, so routing to taiwan_top_traded is left implicit.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.