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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description goes beyond them by disclosing the returned fields (userId + opt-out state; id + status pending/verified/unsubscribed) and two hard constraints: only verified external addresses can be referenced, and free-text addresses are rejected. No pagination/auth notes, but useful context is added.

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?

Two dense sentences, front-loaded with the resource definition before the ref-format detail, and no filler. It could be tightened by moving the ref syntax (which describes another tool's input) out, but each sentence carries real information.

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 parameterless read-only listing with no output schema, the agent needs to know what comes back and any constraints on the values — both are supplied (member/address fields, statuses, verified-only, no free-text). What is missing is the retrieval mechanics (pagination, ordering) and any sibling-usage routing.

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?

The tool takes zero parameters, so the baseline is 4 and there is nothing to clarify schema-wise. The description does add the ref syntax ('role:all', 'member:<userId>', 'ext:<id>') that governs how the enumerated recipients are consumed downstream, which is meaningful beyond an empty schema.

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 states the resource precisely — 'who the org's flows can email with the Send email notification step' — and enumerates the two categories returned (team members and outside addresses) with their fields. It is clear enough to distinguish the resource, but it never names or contrasts with the sibling mutation tools (neuron_add_notify_recipient / neuron_remove_notify_recipient) that operate on the same collection.

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?

Usage is only implied: the description explains that this data feeds the `recipients` field of the Send email notification step and how to format refs there, which suggests when the output matters, but it never states explicitly when to call this tool versus listing members, contacts, or using add/remove notify recipient. A competent agent can infer the context but no exclusion guidance is given.

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