econometrics

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and openWorldHint=true, so the agent knows this is a safe, cached, external-data operation. The description adds no meaningful behavioral traits beyond what annotations provide — no mention of rate limits, data-source constraints, or output behavior. With annotations covering the safety profile, a 3 is appropriate for adding little extra context.

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 first sentence front-loads the test taxonomy, and the second sentence provides usage context and a key parameter example. However, the 48-item 'Available indicators' list is a repetitive dump of the enum already present in the schema, adding noise and length without new information.

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 a tool with 80 parameters and 48 sub-indicators, the description is surprisingly thin on how to select the correct indicator and which parameter combinations matter. It doesn't cover rate limits, data availability, or output format, though an output schema exists. More context on indicator selection and parameter interactions would be needed for an agent to call this correctly without trial and error.

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 100%, so the schema already documents all 80 parameters, including indicator-specific defaults and required-by relationships. The description only restates the tickers='AAPL' format, adding marginal value beyond what the schema provides, so baseline 3 applies.

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 opening clause names a specific set of statistical tests (unit root, cointegration, Granger causality, ARCH-LM, etc.) on price or return series, which is a specific verb+resource. However, it does not explicitly differentiate from siblings like 'models' or 'performance' that could also involve returns, though the test taxonomy is reasonably distinctive.

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 provides a use case ('pairs-trading/spread-modeling foundations or diagnosing return-series properties') and a required-parameter instruction ('Requires tickers=...'), but there are no explicit when-not-to-use or alternative tool comparisons. The 48-indicator list is a menu, not guidance on selection.

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