partial_corr_pvalue

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

Annotations provide readOnlyHint=true and openWorldHint=false, which cover the non-mutating and closed-world nature. The description adds no additional behavioral context beyond the statistical test; it doesn't mention what happens if 'Z' is omitted, or any edge cases. However, since annotations cover safety, a 3 is appropriate, but there is room for more context (e.g., handling of missing data).

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, dense sentence that captures the essence of the tool. It is front-loaded with the purpose and the null hypothesis, and there is zero waste. Every word is meaningful, and it fits well for a statistical tool with a clear function.

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?

The tool has a rich output schema (not provided in the prompt but indicated), which covers return values. The description does not explain the statistical tests or assumptions (e.g., normally distributed data), but the schema for inputs and outputs is comprehensive. For a simple p-value computation, this is acceptable, but it could benefit from a note on when to use partial correlation versus alternative methods.

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 all 9 parameters are documented with descriptions. The description itself adds minimal value beyond the schema—it only clarifies the role of 'X', 'Y', and 'Z' in the hypothesis, which partially reinforces the schema descriptions. For the other parameters (detail, as_handle, data_path, etc.), the schema is sufficient, so baseline 3 is correct.

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 it computes the p-value for a partial correlation test, with the null hypothesis explicitly given as 'X Y | Z'. It specifies the verb ('p-value for'), the resource (partial correlation), and the conditioning structure, which distinguishes it from generic correlation or regression tools. Although siblings like 'test' and 'partial_identification' exist, the description's specificity is sufficient to differentiate.

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 does not explicitly state when to use this tool versus alternatives like 'test' or 'discos_test'. It implies usage by naming the statistical test, but lacks guidance on context (e.g., testing conditional independence) or exclusions. With 9 parameters and a rich schema, this gap is noticeable, but the purpose is clear enough for an agent to infer.

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