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

Annotations already cover read-only, idempotent, non-destructive and closed-world behavior, so the bar is lower, yet the description still adds real value: it discloses the data basis (90 days of observed history) and enumerates the returned signals (verdict, percentile, median, all-time low, sample size). The sample-size mention is especially useful for judging confidence; only caching/latency and coverage limits are unstated.

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?

Two sentences, front-loaded with the question the tool answers and the data window, with the output fields packed efficiently. The closing "No other public source computes it" is mildly promotional but does help justify calling it, so it only slightly dilutes the economy.

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?

Only two simple required parameters and no output schema, so the description carries the return-value burden and does so by listing the concrete outputs. Nothing an agent needs to call it correctly appears to be missing.

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% and the schema itself already specifies city names with the explicit exclusion of airport codes. The description adds only "for a route," so the schema does the real work and the baseline 3 applies.

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 names a specific capability — a "buy now or wait?" verdict for a route computed from 90 days of observed prices — and explicitly contrasts it with flight search ("it judges a price"). That separates it from a generic search tool, but it never differentiates itself from the sibling when_to_book, which is the most plausible source of confusion.

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 implies the usage context (you already have a price and want a judgment for a route) and rules out use as a fare-search tool. Beyond that there is no explicit guidance on when to pick this over when_to_book or cheapest_months, nor any precondition such as needing an existing fare to judge.

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