get_technical_analysisTechnical levels for one or more covered stocks (KR/US/HK/CN/JP/TW/EU) from the precomputed cache: price, MA5/20/60/120, RSI14, Bollinger position, support/resistance, 52-week range, momentum, volatility, trend, and a 0-100 signal score. Accepts tickers or Korean/English company names.
| Name | Required | Description | Default |
|---|---|---|---|
| tickers | Yes | Tickers or company names (KR/EN), up to 25. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already convey read-only, idempotent, and non-destructive behavior. The description adds valuable context: data comes from a precomputed cache (potential staleness) and enumerates the exact output fields, which is helpful given no output schema. No contradiction with annotations.
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?
The description is two sentences long, front-loaded with the core purpose, and each detail (markets, cache, indicators, input flexibility) earns its place. No redundant or fluff content.
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?
Given the tool has one well-documented parameter and no output schema, the description adequately covers the input (tickers/names), market scope, data source (cache), and output contents (indicator list). It omits edge cases like partial failures, but for a simple getter, this is sufficient.
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?
The schema already documents the 'tickers' parameter fully (tickers or KR/EN comments, up to 25). The description repeats this and adds the list of supported markets, but that is supplementary context rather than new parameter syntax. Baseline of 3 is appropriate due to full schema coverage.
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 the tool's purpose: fetching precomputed technical levels for covered stocks, and it lists specific indicators (price, MAs, RSI, etc.). It distinguishes from siblings by focusing on data for given tickers, but does not explicitly contrast with screen_technicals or search.
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?
The description implies usage for retrieving technical data for specific covered stocks and mentions the precomputed cache, suggesting suitability for quick lookups. However, it does not explicitly say when to use this tool over screen_technicals or search, nor does it mention limitations like stale cache data.
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.
fetch and get_technical_analysis overlap in retrieving technical data for a stock, though fetch provides a full record while get_technical_analysis is limited to cached levels. search, list_covered_stocks, and screen_technicals are more distinct but still share the browsing/screening space.
The naming mixes short verbs (fetch, search) with longer verb_noun phrases (list_covered_stocks, screen_technicals) and a verb_adjective_noun (get_technical_analysis). The patterns are not consistent, but all names are readable and actions are inferable.
With 5 tools, the server is well-scoped for a technical analysis domain. Each tool addresses a core need: retrieve, analyze, list, screen, and search, without excess or redundancy that would bloat the surface.
The domain is stock technical analysis, and the tool set covers the essential operations: fetching detailed records, accessing technical indicators, browsing the universe, screening, and searching. There are no obvious missing functions for read-only technical analysis.