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

Annotations already declare readOnlyHint/idempotent/non-destructive, yet the description still adds real behavior: prices are returned 'exactly as captured' with shipping excluded, verdicts are only computed on exact strength/pack matches and never scaled, and unmatched names land in not_found. It also discloses cost (one internal price lookup per call) and the cost-only scope plus the 'not insurance' disclaimer. Minor deduction for burying these traits in one long paragraph rather than stating them as discrete guarantees.

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 trigger conditions are correctly front-loaded, but the remainder is a single dense block with nested parentheticals ('price, pack, strength, origin, source pharmacy, capture date; shipping not included', '(Florida example)') that make it hard to scan. The information is largely useful, but the packaging costs readability.

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?

With no output schema, the description carries the full burden of return semantics and does so thoroughly: per-medicine fields, verdict enumeration (lower_here, lower_canada, same, compare_packs, no_price), Medicare-negotiated-list flag, and the returned links. Nothing an agent needs to call this correctly or interpret the result is 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 coverage is 100%, so the baseline is 3; the description still adds usable meaning by clarifying that names may be brand or generic, English or Spanish, in any capitalization, and that the ZIP drives both nearby pricing and the state-page link. It does not add format or examples beyond what the schema already carries, so it stops short of a 5.

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 the exact comparison performed (Canadian last-listed price vs. today's lowest LowerScript cash price near a ZIP) and the inputs that drive it. It is clearly distinguishable from the price-check sibling, which it references as the fallback for names not on the Canada list.

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?

Opens with concrete trigger scenarios ('buying prescription medicine from Canada', 'what the new U.S. Customs mail-import date... means for a Canadian mail-order refill') and states exclusions explicitly: clinical questions are refused, and ZIPs must be in one of eight served states. It also defines the fallback path via not_found pointing at the price check.

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