stock_tech_indicators_easytdx

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

With no annotations, the description carries the full disclosure burden and does solid work: it states the auth requirement (无需 API Key), the failure mode (returns {error} when easy_tdx is unavailable or there is no market data), and the return shape (latest-period indicator JSON). It does not cover data freshness, rate limits, or caching, but the essential operational behaviors an agent must know are disclosed.

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?

Four information-dense sentences with no filler: purpose, indicator scope, sibling positioning, return behavior, subset parameter, and error case each earn their place. The most decision-relevant facts are front-loaded before the parameter and error details.

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?

For a 4-parameter calc tool with no annotations, the description covers the key operational facts: data source, scope, differentiation from the primary sibling, subset behavior, and error handling. Gaps remain in the full list of the 34 indicators and the semantics of count and market values, though the output schema covers return structure. It is mostly complete but not exhaustive.

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 has 0% description coverage, so the description must compensate for parameter meaning. It explicitly documents indicator_names (subset selection; omission returns all) and implies symbol and market semantics from 'A股' plus the SH default, but count (default 400) is left unexplained in both the schema and the description. This partial compensation covers the most distinctive parameter while leaving at least one parameter ambiguous.

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 states a specific verb and resource: computing 34 A-share technical indicators via easy_tdx, and names four example indicators (WR/BIAS/MTM/ROC) that the default system does not output. It explicitly positions itself as the supplementary backup source for stock_tech_indicators, distinguishing it from that sibling and the HK/US indicator variants. An agent can tell what this tool does and how it differs without opening the schema.

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 names the alternative directly ('作为 stock_tech_indicators 的补充后备源') and signals the use condition: it supplies indicators the primary source omits and acts as a fallback. The error note ('easy_tdx 不可用或无行情时返回 {error}') also tells the agent when the tool will fail. It lacks an explicit when-not-to-use statement, but provides clear context for choosing it over alternatives.

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