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

The annotations declare readOnlyHint=false on what looks like a pure lookup, and the description resolves that apparent oddity by explaining it 'Uses one read and saves the result in the user's Puley history' — a side effect the agent would otherwise not anticipate. It also discloses the not-carried case ('Says so when Cost Plus doesn't sell it'). It does not mention auth, rate limits, or freshness of the published price list.

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?

Front-loaded with the core answer (what the drug costs without insurance, and the source), then the returned fields, then the caveats. The long enumeration sentence is dense but each clause maps to a distinct output field. Slightly tighter punctuation and a shorter history note would make it cleaner, but nothing is padding.

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?

No output schema exists, and the description fully carries the return contract: per strength and form, 30/60/90-pill pricing including the pharmacy fee, shipping-inclusive total, and in-stock status. Combined with the source, the miss behavior, and the history-write note, an agent has everything needed to call this correctly and interpret the result.

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 0% schema description coverage and only bare titles, the description compensates by defining both parameters semantically: drug accepts generic or brand names with concrete examples (atorvastatin, Lipitor), and strength is shown as '10mg'. It leaves one gap: strength defaults to empty and the description never says what omitting it does (presumably return all strengths).

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 — the out-of-pocket cost of a prescription drug at Cost Plus Drugs, sourced from its published price list — and enumerates what is returned (strength/form, 30/60/90-pill prices with pharmacy fee, total with shipping, stock status). This clearly separates it from the price siblings (gas_prices, ticket_prices, subscription_prices, resale_prices) without needing to name them.

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 scope phrase 'without insurance at Cost Plus Drugs' tells the agent when this applies and implicitly when it does not (insurance pricing, other pharmacies), and 'Says so when Cost Plus doesn't sell it' sets expectations for misses. 'Prices only, not medical advice' is a useful exclusion. It stops short of explicitly routing to any alternative for non-Cost-Plus pricing queries.

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