Pillwise

Search medications

search_medications

Read-onlyIdempotent

Typeahead search by what a person calls a medication: brand, ingredient or everyday name. Returns brand and ingredient groups in the order a person would pick, not packages.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "search_medications"
  }
}

Input Schema

Name	Required	Description
`as_of`	No	Optional. Answer as of this day (YYYY-MM-DD) or instant (RFC 3339), up to a year back.
`limit`	No	Hits to return (default 10).
`query`	Yes	What the person typed, at least 3 characters, like "tylenol" or "vitamin d3".

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 28, 2026

changedInput schema / properties / as_of / description

Previous value: -"Optional. Answer as of this day (YYYY-MM-DD) or instant (RFC 3339), within retained snapshots."New value: +"Optional. Answer as of this day (YYYY-MM-DD) or instant (RFC 3339), up to a year back."

First observedOct 17, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, closed-world), and the description goes beyond them by disclosing the shape and ranking of results: results come back as brand and ingredient groups ordered the way a person would pick, not as packages. It doesn't cover default result count or how the as_of lookback behaves, but that is secondary here.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no filler; the search modality and match semantics lead, and the result-ordering caveat follows. Every clause carries information the agent needs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description carries the return-value burden and does explain grouping and ordering. It is slightly thin on what a hit contains (identifiers, whether it is directly passable to get_drug or get_packages) for a discovery tool feeding a large sibling set.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, and the description adds meaning by telling the agent that the query may be a brand, an ingredient, or an everyday name — a semantic dimension the schema's 'what the person typed' does not convey. The explicit note that results are not packages further clarifies what the query matches against.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and modality ('typeahead search') and a clear resource ('medication'), plus the three name forms it accepts (brand, ingredient, everyday name). The closing 'not packages' implicitly separates it from package-oriented siblings like get_packages, so an agent can route without opening a schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The word 'typeahead' plus 'what a person calls a medication' implies the autocomplete-when-the-user-types-free-text scenario, and 'not packages' hints at where get_packages belongs. But no sibling (lookup_rxcui, lookup_ndc, get_drug) is named and there is no explicit when-not statement, so the routing is left to inference.

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

All Pillwise tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?