get_emas

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

No annotations are provided, so the description carries full burden. It discloses that data is derived and not from the exchange, which is useful, but it does not mention other behavioral aspects like potential lag, rate limits, or whether it includes only closed candles vs current forming candle. It also doesn't mention what happens with invalid periods or symbols.

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 compact and front-loads the core purpose. The additional detail on periods and the derived nature is relevant, but the sentence about being derived could be integrated more cleanly. Overall, it avoids unnecessary verbosity and stays focused.

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?

There is an output schema (though not shown here), which may cover return values. The tool is relatively simple with 4 params, but the 0% schema coverage and lack of annotations mean the description must explain both parameters and behavior. It partially does, but the gaps on limit, interval, and error handling reduce completeness.

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?

Schema description coverage is 0%, so the description must compensate. It explains the 'periods' parameter format and semantics, but does not clarify 'limit', 'symbol', or 'interval' beyond their names. It provides no context on how these affect the output or what values are expected (e.g., interval format).

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 returns current EMA values based on real candle closes, and specifies the output includes EMA value, whether price is above, and distance percentage. It distinguishes itself from raw kline data by noting it's derived, which helps set it apart from siblings like get_klines.

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?

It mentions that periods is a comma-separated list and that it's derived from live klines, not an exchange data point, implying usage context. However, it does not explicitly state when to use this over siblings like get_indicators or detect_fvg, nor does it explain when not to use it.

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