Find supplement-supplement interactions (765 pairs from clinical evidence) and drug-supplement interactions (1,626 FDA-validated pairs). Returns synergies, antagonisms, absorption conflicts, and timing recommendations.
| Name | Required | Description | Default |
|---|---|---|---|
| supplement | Yes | Supplement name | |
| include_drug_interactions | No | Include FDA drug-supplement interactions |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It meaningfully discloses what the tool returns (synergies, antagonisms, absorption conflicts, timing recommendations) and the evidence sources (clinical evidence, FDA-validated). However, it does not detail return format, pagination, or failure modes, which are gaps.
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 two sentences, front-loaded with the core purpose, and every clause adds useful information (sources, counts, output categories). There is no repetitive or verbose 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 the tool's moderate complexity, no output schema, and no annotations, the description provides enough context: it states the scope, data sources, and high-level result categories. It falls short only in not describing exact response structure or potential limitations, but for a lookup tool this is reasonably complete.
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 the input schema already fully describes both parameters ('supplement' and 'include_drug_interactions'). The description adds no additional parameter-level detail, so it neither improves nor harms parameter understanding.
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 uses a specific verb 'Find' and clearly identifies two distinct resources: supplement-supplement interactions and drug-supplement interactions. It distinguishes itself from sibling tools like get_supplement_info and get_biomarkers_for_supplement by specifying interaction types and quantified data sources.
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 implies the tool is used when interaction data is needed, but it does not explicitly state when to choose it over siblings or provide exclusion criteria. There is no mention of alternatives such as get_supplement_info, so the guidance is only implicit.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Add one secure layer between your agents and this server.
Most tools target distinct resource-action pairs, but get_supplements_for_biomarker and get_interventions_for_biomarker overlap in purpose (both return things affecting a biomarker), with the key difference being intervention type filtering. This could cause misselection if the agent does not read descriptions carefully.
All tools follow a consistent verb_noun pattern using snake_case (get_* and search_*). Naming is predictable and clearly groups resource types, with no mixed conventions or vague verbs.
With 9 tools, the set is well-scoped for a supplement and biomarker information server. Each tool addresses a distinct functional need without redundancy, falling comfortably in the ideal 3-15 range.
The tool surface covers the primary workflow: searching supplements/conditions, retrieving supplement details and biomarkers, finding supplements/interventions for biomarkers, checking interactions, and getting brand quality data. Minor gaps exist, such as no direct biomarker search or tool to get conditions for a supplement, but core use cases are covered.