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

Annotations already declare readOnly=true, idempotent=true, openWorld=true, so safety is covered; the description adds real value on top with data-coverage caveats (US-only, no bulk ingredients, missing delisted products) and a cost of 1 credit. It does not discuss result ordering or behavior when an NDC matches nothing, which keeps it off a 5.

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?

It is front-loaded with a framing question and the core lookup statement, followed by format examples, returned fields, audience, source, and caveats. Dense rather than bloated, though the parenthetical format examples are largely redundant with the schema and could be trimmed.

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?

For a read-only reference lookup with no output schema, the description explicitly enumerates what comes back (labeller, active ingredients and strengths, dosage form, route, OTC vs prescription, approval reference, pack sizes) plus source and coverage limits. An agent has everything needed to decide to call it and to interpret the response.

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 all three parameters are already documented in the schema. The description restates the NDC formats (product, package, 11-digit billing form) and the name-or-NDC choice, which duplicates rather than extends the schema; the 'limit' behavior is left entirely to the schema. Baseline 3 is appropriate.

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 opens with a specific verb and resource combo: 'Looks up US medicine products in the FDA National Drug Code Directory by brand or generic name or by NDC.' It names both lookup keys and the fields returned, which clearly separates it from siblings like fda_drug_shortages and fda_drug_side_effects_reported even before opening the schema.

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 gives a concrete usage context ('pharmacy, billing and supply-chain work') and, more usefully, explicit exclusions: US-listed products only, name searches exclude bulk ingredients, and delisted products are absent. It stops short of naming a sibling alternative when a user really wants shortages or adverse events, so it is strong but not a full when/when-not/alternative map.

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