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

Annotations only certify readOnly/openWorld=false, but the description goes well beyond that: full cost model ($0.005/request + $0.0002/record, less past 100, capped at $0.50), plan gating (pay-as-you-go, Understanding, Influence), an estimate endpoint, and a hard data-shape limit ('facet rollups cannot name the checks underneath them'). This is exactly the extra context annotations cannot carry.

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 intent statement is front-loaded in the first clause and no sentence is pure filler, but roughly half the text is pricing/tier boilerplate that could have been a single pointer to the prices resource. Efficient, though not maximally tight.

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 does describe the result conceptually (failing checks ranked by lift to the cohort mean) and covers access tier and cost. Remaining gaps — exact record shape and pagination interaction with the per-record price — are minor for a read-only cohort query.

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 kind, slug, page, limit and context are already fully documented in the schema. The description adds no syntax, format, or example detail beyond that ('Named checks only' constrains output shape, not parameters). Baseline 3 is correct when the schema does the heavy lifting.

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?

Specific verb+resource: it returns the agent-readiness checks a cohort most commonly fails, ranked by impact on the cohort mean. It differentiates from the nearest sibling explicitly ('The inverse of gap_analysis, which says where a market is under-served; this says where it is failing the rubric'). An agent can select this without opening any other schema.

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?

Names the alternative (gap_analysis) and the condition that separates them, and adds a real usage constraint ('Named checks only — facet rollups cannot name the checks underneath them'). It does not, however, route among the other cohort_* siblings (cohort_scores, cohort_rankings, cohort_capabilities, cohort_stats), so the guidance is clear but not exhaustive.

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