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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered; the description adds value by stating the preview returns click counts, day span and current booked cost, and by explaining how the segment is composed. It does not mention permission requirements for sensitive filters (the schema notes the 'See statistics per team member' permission for `user`) or what an empty segment returns.

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?

Three tight sentences with the no-write guarantee front-loaded, followed by a compact definition of the segment and the dry-run classification. No filler, and the most decision-relevant information comes first.

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 57-parameter read-only preview with no output schema, the description is substantially complete because it describes what the dry run reports (click counts, span, current bookings) and what constitutes the segment. Missing only edge-case behavior such as empty-segment results or permission-dependent filters, which are partly covered in the schema itself.

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 57 parameters and 88% schema description coverage, the schema already documents nearly every filter, so baseline 3 applies. The description adds only a light summary of the filter families and the comma-separated convention for campaign aliases, without clarifying combination semantics (AND across filters) or how period interacts with date_from/date_to beyond what the schema says.

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 ('preview a segment cost update') and immediately defines the scope as a dry run that changes nothing. The phrase 'The dry run of a segment cost update' implicitly distinguishes it from the apply-side sibling set_segment_costs, so an agent can pick the preview tool without opening either schema.

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 'WITHOUT changing anything' / 'dry run' framing gives a clear condition for selecting this tool before a real cost update. It stops short of explicitly naming set_segment_costs as the follow-up action or stating when a preview can be skipped, so it is strong context but not a full when/when-not/alternative map.

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