correlation_matrix

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

No annotations are present, so the description carries the full behavioral burden, and it does so extensively: scipy pairwise .statistic/.pvalue, pandas corr rejected for lacking p-values, kendall/kendalltau alias behavior, BH-FDR correction on computable upper-triangle pairs, constant-column nulls, and numeric-column error thresholds. It also discloses the success/error response envelope.

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 organized into labeled sections—params, return, 口径, examples, inline_data—and most content is operational detail earned by the absence of annotations and output schema. Meta sentences like 'docstring = agent 使用说明书' and '红队裁决 11' add maintenance context rather than invocation value, so it is not zero-waste.

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?

It covers all essential invocation information: complete result structure, null semantics, correction unit, pairwise-complete handling, method aliases, examples, and rejection conditions. The only material deferral is inline-data scale/type rules pointed to an external SPEC document, which may not be available to the agent.

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% and there are no enums, so the description is the only source of parameter meaning. It documents all four parameters with formats, allowed values, defaults, and side effects, including inline_data's two accepted shapes and mutual exclusivity with file_path.

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 identifies the tool as a correlation matrix in the data-exploration group and details its method options and result fields (correlation, p_value, n_pairwise), so the tool's job—computing pairwise correlation matrices—is clear. It lacks an explicit verb like 'calculates' and does not state how it differs from siblings such as plot_heatmap or hypothesis_test, so it stops just short of the highest tier.

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 intended use is implied by the tool's placement in the data-exploration group and by constraints like '数值列 >20 拒绝' and '<2 列拒绝', which tell an agent when the input is unsuitable. It never explicitly states when to choose correlation_matrix over a sibling tool and gives no alternatives or exclusions.

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