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

Annotations already declare the tool read-only, idempotent, and non-destructive, and the description adds meaningful behavioral detail: it enumerates the returned fields (status, indication, active substance, ATC code, holder, regulatory flags) and the date history scope. This goes beyond the annotations and helps an agent understand what to expect from the call.

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 description is detailed yet efficient: a front-loaded, specific main clause followed by a compact field inventory and example queries. Every sentence contributes useful operational knowledge with no redundant or filler content.

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?

Given a simple single-parameter input and no output schema, the description sufficiently explains both the input format and the rich return payload. It also gives representative user intents, making the tool's role and behavior clear to an agent without needing external context.

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?

The schema already covers the single parameter with 100% description coverage, but the tool description adds valuable context by giving the EMA product number format (EMEA/H/C/...) and concrete examples for both accepted lookup types. This enriches the schema's brief 'Brand name, INN, or EMA product number' description.

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 clearly identifies the tool's action: returning a full European Medicines Agency record for one medicine. It specifies the lookup keys (brand name or EMA product number) and distinguishes this from the list-oriented sibling ema_medicine_search by emphasizing 'full record' for a single medicine.

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 description states exactly how to invoke the tool: by brand name, INN, or EMA product number, providing examples of each. It implies the correct use case (looking up a specific medicine) versus searching for medicines, but it does not explicitly name ema_medicine_search as an alternative or state when not to use this tool.

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