Screen Korea's KOSPI exchange (Samsung, SK Hynix, Hyundai, LG, etc.).
Args: criteria: filter dict (industry, market cap, P/E, etc.) limit: max rows to return
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | ||
| criteria | No |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint and openWorldHint. Description adds minimal behavioral context beyond screening capability. No disclosure of pagination or data freshness.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences plus parameter list, concise and front-loaded. Could add more structure but is efficient for the information provided.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Covers purpose and parameters adequately for a simple tool. No output schema, so return format is not required. Minimal but complete given context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
With 0% schema coverage, description fully explains both parameters: limit as max rows, criteria as filter dict with example fields (industry, market cap, P/E). Adds essential meaning.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it screens the KOSPI exchange with examples of major companies. The name and sibling tools make the target market unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No explicit guidance on when to use vs alternatives, but the sibling tools are other exchanges, implying usage for Korean stocks. Lacks conditions like when not to use.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Each tool targets a distinct geographic exchange, with no overlap in markets screened. The descriptions specify the exchange and indices, making it easy for an agent to select the correct tool for a given country.
All tools follow the exact same naming pattern: 'screen_<country>_<exchange>' in snake_case, providing a clear and predictable structure. There are no deviations or mixed conventions.
26 tools is on the high side, but appropriate for a global equities screener covering many countries. Each tool serves a distinct market, so the count is justified by the breadth of coverage.
The set covers most major global equity markets, including US, China, India, Japan, and many others. However, some notable markets like Russia or some European exchanges are missing, and there is no tool for screening ETFs or indices directly.