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

Annotations already declare readOnlyHint/idempotentHint/openWorldHint/non-destructive, so the safety profile is covered. The description adds genuinely useful behavior beyond that: per-year status semantics (in effect, ended by deselection, not yet effective, selected but unpublished), a 30-day-equivalent normalization basis, and CMS sourcing with data_as_of for provenance. Its only miss is not flagging any latency or coverage caveats.

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 core action, and every clause carries information. The parenthetical status list is dense but earns its place because it defines the values the caller will actually see in the response.

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 a full schema, an output schema, and rich annotations, the description supplies the remaining needed context: accepted identifier types, year coverage, status meanings, provenance fields, and the negative-result contract. Nothing essential is missing, though a pointer to the sibling listing tool would close the last gap.

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 both parameters are already documented, including the year enum and default. The description's restatement of brand/generic/NDC forms and the 2026-2028 years largely duplicates the schema examples rather than adding new semantics such as how ambiguous names are resolved or whether year filters the returned price years.

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 gives a specific verb ('look up') and a precise resource ('Medicare negotiated Maximum Fair Price for a drug selected under the IRA drug price negotiation program'), and enumerates the three accepted identifier forms. It does not name the obvious sibling mfp_selected_drugs, so the selection split between 'look up a price' and 'list selected drugs' must be inferred from context rather than stated.

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?

Usage context is clear: call this when you need the negotiated price for one specific drug, and the description states what happens when the drug is not on any selected list (selected:false, explicit statement, never a zero price). It stops short of naming alternatives or exclusions, e.g. when to prefer mfp_selected_drugs for enumerating the program list.

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