correlation_analysis

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

With no annotations, the description carries the behavioral burden. It discloses the core behavior (Pearson correlation matrix on numeric columns) and implicitly that it is read-only, but it omits behavior for non-numeric columns, missing values, source selection, and output formatting.

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 a single short sentence with no filler. Every word adds information, and the core object (numeric-column Pearson matrix) is front-loaded.

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?

A simple output schema may cover return values, but the tool still has three undocumented parameters and no annotations. The description alone does not give an agent enough to know valid format/source values or behavior with defaults, so it is incomplete.

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 explain the three parameters. It only clarifies that columns are optional; format and source are left unexplained. This is insufficient for correct invocation.

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 operation as computing a Pearson correlation matrix over numeric columns and notes optional column selection. This is specific enough to distinguish it from generic aggregate_stats or sql_query, though it is a noun phrase without an explicit verb and does not name alternative tools.

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?

No when-to-use or when-not-to-use guidance is provided, and no alternatives are mentioned. '可选指定列' hints at usage, but the agent gets no context about prerequisites, typical scenarios, or why to choose this over sql_query/aggregate_stats.

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