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

Annotations already establish non-read-only, non-destructive, non-idempotent, open-world behavior, and the description adds real value on top: rules are validated before any API call, dry_run previews, custom fields are not yet accepted, and a rule cannot target one specific campaign. The score is capped because it never says what happens on a duplicate name (schema notes uniqueness) or what is returned on success.

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 purpose is front-loaded, but the body is one dense paragraph of highly technical material with no bullets or grouping, making the operator and activity rules hard to retrieve. Several clauses restate the schema's field descriptions verbatim, so the wall of text carries cost without adding 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 5-parameter create tool with a nested rule array, no output schema and full annotation coverage, the description covers creation semantics, the rule model, validation, preview and known API limitations, which is close to sufficient. It lacks only post-creation behavior (whether the segment evaluates immediately, error shape on invalid rules).

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 100% schema description coverage the baseline is 3, and the description earns above that by explaining cross-field dependencies the schema only hints at: which filter_type each operator family belongs to, that mailbox_provider/signup_source take was or was_not, that property_type picks the operator family, and that certain operators take no value or an array. Two worked examples make the nested rule object concrete in a way the flat schema cannot.

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?

"Create an audience segment: a saved, dynamic filter over contacts" gives a specific verb plus resource and defines what a segment actually is, which no sibling name makes obvious. The rule-model vocabulary that follows immediately distinguishes it from create_list, create_tag and update_segment.

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?

It states the operative mechanics (match all|any, lists narrows the base, omitted = all contacts) and explicitly points at dry_run for preview, which tells the agent when to use the preview path. It never names the alternative tools (list_segments, update_segment, delete_segment) or states exclusions, so it stops short of full routing guidance.

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