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

The description adds significant behavioral context beyond the readOnlyHint and destructiveHint annotations: it explicitly says the segment is not saved, returns an estimated size, provides a known limitation about combining attendance and spending criteria in the same stanza, and mandates modifier rules. This is valuable operational guidance an agent cannot derive from annotations or schema alone.

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 description is longer than average, but the complexity of the segment DSL justifies much of the length. The purpose is front-loaded, and every major rule is actionable; however, some details, such as entity array syntax and time_range.value > 0, are already present in the schema and are therefore somewhat redundant.

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?

Given the rich input schema, the readOnly/destructive annotations, and the absence of an output schema, the description fills the remaining gaps: it explains what the tool returns, that it has no persist effect, and provides the domain-specific constraint needed to construct a valid preview definition. It is sufficiently complete for an agent to invoke the tool correctly.

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 the schema already documents value types, operators, modifiers, and stanza semantics. The description reinforces the most failure-prone rules (single string OR array for ENTITY operators, omit modifiers unless requested, time_range.value must be > 0) and adds the critical non-obvious rule about separating attendance and spending criteria, which is not in the 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 opens with a specific verb-resource pair: 'Preview estimated audience size for a segment definition without saving it.' It clarifies the tool is a read-only estimation action rather than a save or execute action, distinguishes it from siblings like nevent_create_segment and nevent_segment_execute, and states the concrete outputs (fan count and sample contacts).

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?

The description establishes clear context: use this when you need an audience estimate for a segment definition before saving or executing it. It does not explicitly name alternative tools or state when not to use it, but the 'without saving it' framing and sibling set make the intended usage inferable.

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