cohens_h

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the core safety profile is covered. The description adds valuable behavioral context: it returns a float that can be negative, the sign indicates direction, and provides the standard interpretation thresholds (0.2/0.5/0.8). This exceeds what annotations alone convey, though it does not discuss edge-case behavior (e.g., proportions at 0 or 1) or error handling.

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 sentences but packed with essential information: the transform rationale, interchangeability, usage relationship, return type, and interpretation scales. Every clause earns its place; no redundancy or filler.

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 statistical function, the description covers all major aspects: what it computes, why it's appropriate, how to use it with a sibling tool, the return type, and interpretation guidance. The output schema likely just indicates a number, so no further return-value explanation is needed. No significant gaps detected.

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 coverage is 100% (both p1 and p2 have 'a proportion in [0, 1]' descriptions). Beyond that, the description adds that p1 and p2 are interchangeable and that the sign of the result only indicates direction, which is not present in the schema. This provides meaningful additional meaning, so it scores above the baseline of 3.

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 that it computes an effect size for a difference between two proportions via the arcsine-square-root transform, explicitly distinguishing it from a raw percentage-point difference. It names the resource (two proportions) and the specific action (compute effect size), and the context distinguishes it from siblings like cohens_d (for means) and two_proportion_z_test (significance testing).

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 explicitly instructs to 'use alongside two_proportion_z_test' and explains that the z-test tells significance but not size, directly addressing when to use this tool. It also notes interchangeability of p1 and p2, providing clear usage guidance and naming an alternative.

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