get_correlation

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

With no annotations provided, the description carries the burden of revealing behavior. It discloses the available methods (pearson, spearman, kendall) and that it returns a value and interpretation, which covers the core behavior. However, it does not mention whether it operates on the current dataframe, how missing values are handled, or any read-only guarantees, leaving some ambiguity about side effects and prerequisites.

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 relatively short but contains redundancy: 'Compute pairwise correlation between two numeric columns' and 'Measure relationship between two numeric columns' say essentially the same thing. The example is useful, but the repetition adds unnecessary words without new information, making it slightly less concise than it could be.

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?

For a 4-parameter tool with no schema descriptions and no annotations, the description is incomplete. It explains the core purpose, methods, and usage context, but omits the df_name parameter entirely, which is needed for full invocation control. The presence of an output schema helps with return values, but the parameter gap and unclear dataframe scope make this insufficient for confident tool use.

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 all parameters. It clarifies col_a and col_b as numeric column names and lists valid method options, and the example demonstrates the parameter syntax. However, the df_name parameter is completely ignored, leaving it undocumented, which is a significant gap given the absence of any schema descriptions.

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 the tool computes pairwise correlation between two numeric columns, lists the supported methods, and explains it returns a value and interpretation. It also distinguishes itself from the related plot_correlation_matrix tool by positioning itself for targeted follow-up investigation, making the purpose explicit and differentiating it from siblings.

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 gives a clear usage scenario: 'Use for targeted investigation after plot_correlation_matrix reveals interesting pairs.' This tells the agent when to apply this tool versus the broader visualization alternative. It does not explicitly mention other alternatives like correlation_filter, but the provided guidance is enough for typical use cases.

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