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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description adds real value: the result set semantics ('everyone, not only emailable'), reachability breakdown by email/sms/app, excluded-by-reason counts, coverage notes, the 'exact' flag, and the privacy constraint 'No emails or phones in rows'. These disclose behavior the annotations cannot.

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?

It is front-loaded with the core purpose, but the body is a single dense run-on packed with parentheticals and semicolons that is hard to parse on first read. Information density is high, yet restructuring into short clauses or bullets would materially aid comprehension without losing content.

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 8 parameters, nested rule objects and no output schema, the description correctly compensates by describing the return payload (matched set, reachability, excluded-by-reason counts, plainRule, exact, coverage notes) and pagination via exact/cursor. The nesting/grouping semantics (group 0-9, AND/OR) are left to the schema, a minor gap.

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?

With 75% schema coverage the baseline is 3, and the description earns above it by tying the concepts together: 'eventIds + scope any|sum and since/until dates', 'limit ≤50', the top_by options, and cursor/exact linkage. It does not add format detail beyond the schema, but it surfaces the key combinations an agent must reason about.

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 and resource ('Who among your guests/members') and pins the query language ('rules in the email studio's condition format'), so an agent knows this is a rule-based audience query rather than a plain listing. It does not explicitly name the siblings it competes with (list_guests, save_people_as_list, build_list_from_events), which keeps it below a 5.

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?

Implicit guidance exists through the enumeration of modes ('count (first)', 'sample', 'top by ...; limit ≤50'), which tells the agent which mode to pick for which goal. However, there is no explicit when-to-use versus alternatives, no statement of when not to use it, and nothing routing the agent to save_people_as_list or list_guests.

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