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

Adds real context beyond the annotations: it discloses the upstream network (LowerScript/RxSense), that results include card codes, a wallet-pass link and a lowerscript.com page, that the full price spread is shown rather than just the cheapest, and that it hard-refuses clinical questions. Safety profile is already covered by readOnlyHint/idempotentHint, so remaining gaps like auth or rate limits are minor.

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 dense, front-loaded sentences that each carry information; the cheapest-first/not-just-lowest behavior and the state list are the kind of detail an agent needs. Slightly long, but no sentence is wasted.

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 does the work of explaining the return payload (prices spread, card codes, wallet link, web page) and the hard prerequisites (valid served-state ZIP). An agent has everything needed to call it correctly and to know when it will refuse.

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, but the description usefully enumerates the eight served states (FL, TX, AZ, NC, SC, GA, IL, CA) — a constraint not present in the schema — and reinforces the ZIP-over-city/state rule. It adds genuine meaning beyond 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?

States a specific verb+resource (live cash prices for one drug at nearby pharmacies) plus scope detail (up to 10, cheapest first, full spread). An agent can immediately distinguish this from find_drug (name resolution) and get_card (card retrieval).

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?

Gives explicit constraints: one drug per call, no bulk lookups, requires a 5-digit ZIP in a served state, city/state alone unsupported, and refuses clinical questions. It does not explicitly point to find_drug for resolving an unknown drug name, which is the one routing gap.

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