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

Annotations only declare readOnlyHint, so the description carries the burden of explaining real-world behavior. It adds pricing details (per-request, per-record, cap), plan eligibility, and the estimate-first workflow, which are important non-obvious behavioral traits. It does not cover errors or pagination, but the cost and read-only nature are well disclosed.

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 outcome is front-loaded, and each sentence carries useful information about scope, plan, pricing, or estimation. The pricing clause is dense and uses many clauses, but it is still compact and relevant. There is no filler or repetition.

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 description covers the main return contents, plan gating, and cost, which is good given no output schema exists. It does not describe how to construct kind/slug values, what the output structure looks like, or how roster pagination behaves. Some selection and invocation details are left to the schema and sibling names.

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 only 33% (only context has a description), and the description does not explain kind or slug at all. Required parameters are left to the schema enum and field names, so the description fails to compensate for the low coverage gap.

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?

Describes the resource clearly as a single cohort and enumerates returned contents: identity, population, full member roster, provider Kin Score, and agent readiness. It also distinguishes this from cohort analysis parts (stats/rankings/scores/capabilities), though it does not explicitly name sibling tools. The action is unambiguous via the tool name and title even though no verb appears in the description.

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?

Provides plan context: basic cohort data is available under Understanding, while analysis parts require Influence. It also tells the agent to estimate cost first and points to the pricing endpoint. However, it does not explicitly say when to prefer this tool over sibling cohort_* tools or when to use those alternatives instead.

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