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), so the bar is lower. The description still adds behavior beyond them: it discloses the refusal path for unlisted cities, that it takes no price, that results come from cwsi.net's calculator, and that the tool is unofficial — useful context for trusting/validating output.

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 in the first sentence, but the rest is a single undifferentiated block of reference rules (percentages, dates, rounding) that duplicates the schema rather than adding new information. For a 13-parameter tool the length is defensible, yet structure and non-redundancy suffer.

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?

An output schema exists, so return values need not be explained. Given the complexity (13 params, 8 enums, partner-program path via creditTo), the description covers eligibility, formulas, exceptions, refusal behavior and the unofficial disclaimer, leaving only the creditTo partner flow to the schema.

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 baseline is 3. The description's rule text (base 1,000–7,000, fare-brand percentages, tier bonuses, issued-date cutoffs) largely restates what the schema already documents for brand, issued, status, seat and stock, so the marginal semantic gain over structured fields is limited.

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 opening sentence names the specific resource (Etihad Guest Miles and Tier Miles) and the exact scope (Etihad-marketed and operated flights on a ticket starting 607/291/169, stock EY), which cleanly separates it from the dozens of other airline calculators in the sibling list. An agent knows immediately this is the Etihad earning calculator, not a generic distance or fare-class tool.

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 gives real applicability conditions: rates by fare brand apply only to Etihad tickets, other tickets (stock OT) 'are not worked out' and only return a table, promo seats (seat P) behave differently, and 'A city not on Etihad's list is refused.' It does not explicitly route the agent to calculate_flight_distance or compare_fare_classes, but the when-it-applies/when-it-does-not context is unusually strong.

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