indicator_linreg

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

With no annotations, the description must disclose behavior fully. It states the tool is linear regression and requires a minimum number of points, but does not detail the output (e.g., slope, intercept, or predicted values), error handling for insufficient data, or any side effects. The behavioral information is minimal.

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?

Very short at two sentences, no fluff. The Chinese and English names are redundant but not a major issue. The precondition is important. Could be structured better but overall concise.

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 complexity of linear regression and the lack of output schema, the description fails to explain the return value (e.g., is it a single number or a structure?). It also doesn't place the tool in context among the many sibling indicators. Important gaps exist.

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 describes both parameters (values as price array, interval as calculation period). The description adds the constraint that interval data points are needed, linking the two parameters meaningfully. However, it does not explain how interval is used in the regression calculation or the units.

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 performs linear regression on the values array over a specified interval. The name 'indicator_linreg' and the explicit mention of 'Linear Regression' leave no ambiguity. Among the numerous indicator siblings, this function is uniquely identified as linear regression.

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 only provides a precondition ('requires at least interval data points') but no guidance on when to use this tool versus other indicators like SMA, EMA, or MACD. The agent has no criteria to choose this tool from the sibling indicators.

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