Get Compound Interactions

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

Annotations already declare readOnly, idempotent, and openWorld hints. The description adds valuable behavioral context: data source attribution and that many compounds have no interaction records, which aligns with openWorldHint and helps set expectations.

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 extremely concise: three sentences cover purpose, data sources, and data quality. Every sentence adds value, and the information is front-loaded. 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?

With an output schema present, the description does not need to detail return values. It sufficiently covers the tool's scope, data sources, and caveats. Could add a brief note on pagination if applicable, but not necessary.

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 baseline is 3. The description enriches parameters by explaining the 'kinds' enum with examples (e.g., 'drug-drug (interactions with other drugs)') and notes that well-studied drugs have a long tail, aiding 'maxEntries' usage.

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 states the tool retrieves interaction data (drug-drug, drug-food, target) with source attribution. It does not explicitly differentiate from sibling tools like pubchem_get_bioactivity, but the specific interaction focus is clear.

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 notes that data is richest for approved drugs and many compounds have no records, providing context on data availability. However, it lacks explicit guidance on when to use this tool versus alternatives, such as pubchem_get_bioactivity for purely activity data.

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