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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered; the description goes further with the depth_confounded caveat and depth_note explanation, plus full pricing mechanics (per-request, per-record, cap, plan inclusion, estimate endpoint). It adds genuine behavioral context, though it says nothing about latency, caching, or failure modes.

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?

Front-loads the understanding and return before the caveat and pricing, and every sentence carries information not present in structured fields. The pricing sentence is long and dense but is the only place that cost model is documented, so it earns its place.

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?

With no output schema, the description steps up to describe exactly what comes back (both distributions plus per-dimension deltas), warns about the confound that would otherwise mislead interpretation, and documents the full cost path. Nothing essential to calling it correctly is missing.

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%, including inline examples for a and b and the semantics of context ('never used to rank'). The description adds no parameter-level detail beyond the schema, so the baseline 3 is appropriate.

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?

States a specific verb+resource (side-by-side comparison of two cohorts on one rubric) and spells out the return: both distributions plus deltas on score, agent readiness, every facet and adoption rate. The framing question ('is US payments further along than UK banking?') makes it immediately distinguishable from single-cohort siblings like cohort_scores or cohort_stats.

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?

Gives a clear usage scenario and an implicit when-not ('a report only ever covers one market'), so the agent knows this answers cross-market questions other tools can't. However, it never names a sibling alternative or an explicit exclusion, so routing against the many cohort_* tools is left partly to inference.

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