correlation_matrix

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

No annotations are provided, so the description carries the full burden. It discloses one important behavioral trait: missing-data handling is explicit, which alerts the agent that the tool will not silently drop missing values. However, it does not describe what the tool returns (covered by output schema), how it treats non-numeric data, or any limitations. For a read-only compute operation this is acceptable but sparse.

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?

A single ten-word sentence that front-loads the action and resource. Every word adds information: 'Compute' sets the operation, 'Pearson or Spearman' specifies method options, and 'explicit missing-data handling' flags a behavior. There is no filler or repetition.

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 rich input schema and the presence of an output schema, the description provides enough orientation to know the tool is for correlation computations. But it does not explain when to select pairwise vs listwise deletion, nor does it contrast with descriptive_statistics for univariate analysis. The lack of any annotation means the agent gets no safety or cost context, so a slightly more detailed description would improve 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?

The description maps to two nested parameters: method (Pearson/Spearman) and missing (handling). It adds no detail on the request structure, the expected data shape, or variable_names, leaving that to the schema, which is well-defined with $defs and titles. Since schema prose coverage is 0%, the description only partially compensates for the missing parameter explanation.

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 opens with the specific verb 'Compute' and names the exact resource ('Pearson or Spearman correlations'), immediately distinguishing this from sibling tools like descriptive_statistics or ctt_item_analysis. It also highlights a distinctive feature ('explicit missing-data handling'), reinforcing scope. The only minor omission is not explicitly saying the result is a matrix, but the tool name and verb make that clear.

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 a use case: when Pearson or Spearman correlations are needed. However, it gives no explicit when-to-use versus alternatives, no exclusions, and no guidance on choosing between pairwise and listwise missing-data handling. It does not reference sibling tools or conditions under which a different analysis tool should be preferred.

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