search_supplementsLegacy commerce tool. Search catalog products by name, ingredient, or brand. Results may contain affiliate URLs; use search_evidence for commerce-free clinical evidence.
| Name | Required | Description | Default |
|---|---|---|---|
| goal | No | ||
| limit | No | ||
| query | Yes | ||
| demographic | No | general |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare the operation as read-only, idempotent, and non-destructive. The description adds valuable context by warning that 'Results may contain affiliate URLs,' which is a behavioral trait not covered by annotations. It also calls itself 'legacy,' adding useful context.
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 with no wasted words. The first sentence immediately labels it as legacy, and the second provides purpose plus an alternative. Every sentence earns its place.
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 four parameters, no output schema, and zero schema descriptions, the description is on the thin side. It gives a clear purpose and a key alternative, but the parameter semantics and return format are not addressed. The annotations cover safety, but the tool's full usage context is incomplete.
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 0%, so the description must compensate for the lack of parameter explanations. It only hints at 'query' semantics via 'by name, ingredient, or brand' but leaves 'goal,' 'limit,' and 'demographic' completely unexplained. This is a significant gap.
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's function: 'Search catalog products by name, ingredient, or brand.' It identifies itself as a 'Legacy commerce tool' and distinguishes itself from the sibling tool 'search_evidence' by directing users there for clinical evidence, thus specifying its unique role.
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 provides explicit guidance: it names 'search_evidence' as the alternative for 'commerce-free clinical evidence,' which effectively tells the agent when not to use this tool. The label 'Legacy commerce tool' also signals its position among siblings.
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.
The evidence tools (compare_evidence, get_citations, get_evidence_summary, query_evidence_map, search_evidence) and commerce tools (compare_supplements, get_price_history, get_product, recommend_for_goal, search_supplements) are clearly separated, but a few pairs like compare_evidence vs compare_supplements and search_evidence vs query_evidence_map could cause confusion despite different data sources being described.
All tool names follow a consistent verb_noun snake_case pattern (e.g., search_evidence, get_citations, compare_evidence), making it easy to predict functionality from the name.
The 10 tools are within a reasonable range, but the legacy commerce tools (compare_supplements, get_price_history, get_product, recommend_for_goal, search_supplements) add redundancy and could be trimmed without losing core functionality, making the set slightly over-sized.
The evidence surface fully covers search, summary, comparison, citation retrieval, and dataset querying, while the commerce tools provide complete product lookup, price history, and recommendation capabilities. No major gaps are apparent for the stated purpose.