benjamini_hochberg

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

Annotations declare readOnlyHint=true, so the agent knows this is a read-only calculation. The description adds little behavioral context beyond naming the procedure; it doesn't disclose output shape, assumptions, or side effects. Since the annotation already covers the safety profile, a 3 is appropriate.

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 two short sentences and contains no wasted words. The core identity is front-loaded; the validation note is second. It's appropriately minimal for a self-explaining statistical procedure.

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 simple FDR-correction function with only one required parameter (pvalues) and full schema coverage, the description plus schema are mostly sufficient. The main gap is that it doesn't relate to or distinguish the tool from the multiple-adjustment siblings (bonferroni, holm, romano_wolf), and it doesn't mention whether adjusted p-values are sorted or returned in original order. But output schema exists and the operation is a narrow read-only calculation.

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 parameters are already documented in the schema. The description adds no parameter-specific meaning, but with full coverage the baseline of 3 applies. The detail parameter in the schema already explains payload depth options well.

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 names the Benjamini-Hochberg (1995) FDR correction, which is a specific verb+resource combination. It is distinguishable from siblings like romano_wolf, holm, and bonferroni because it names the exact procedure. However, it doesn't explicitly contrast with those FDR-adjustment siblings, so it loses the fifth point on sibling differentiation.

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 states what the tool is but not explicitly when to use it compared to alternatives. The 'Validation: certified parity evidence' line hints at a use case (validated parity with an established implementation) but doesn't say where it fits among the many multiple-testing siblings. The detail parameter does explain when different payload depths are appropriate, providing a moderate usage signal.

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