Skip to main content
Glama

search_taiwan_drug

Read-onlyIdempotent

Search Taiwan drug registries by NHI code, ATC code, generic name, or brand name. Returns canonical record with billing code, dosage, and classification for NHI billing or clinical documentation.

Instructions

Search Taiwan drugs across NHI and TFDA registries with unified cross-reference. Returns generic name (EN + 中文學名), all brand names + aliases, NHI 9碼 billing code, ATC code, dosage form, strength, route, therapeutic class, applicable specialties, compound-flag, and effective date. The query auto-detects four input shapes: (1) NHI drug code 9碼 (e.g. 'AC4537911', 'A04403412' — 1-2 letter prefix + 6-9 digits) → direct match; (2) ATC code prefix (e.g. 'J01CR02' or 'J01' for the antibacterials class) → class match; (3) Generic name EN or 中文 → ILIKE; (4) Brand name / alias → secondary fallback. Use when an agent has any drug identifier and needs the canonical record for billing / SOAP / appeal context. Typical follow-up: call get_drug_rules({drug_category_query}) for NHI payment rules / prior-authorization on this drug, lookup_icd10_cm for the diagnosis side, or count_appeal_precedents_for_rejection_code if a rejection code is involved. Out of scope: drug-drug interactions, severity scoring, indication-specific dosing. Reference only — TFDA license / 健保 給付規定 are authoritative. Curated by OPDSTAR (https://opdstar.com).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
queryNoSearch term: generic name (EN or 中文), brand name, alias, NHI 9碼, or ATC code. Minimum 2 chars (unless atc_prefix is provided).
atc_prefixNoOptional ATC code prefix to filter / browse by therapeutic class (e.g. 'J01' = systemic antibacterials, 'C09' = renin-angiotensin agents). Can be used alone to enumerate a class.
formNoOptional dosage_form filter (e.g. 'tablet', 'capsule', 'cream', 'ointment', 'inj', 'syrup'). Partial match.
limitNoMax results (1..30). Default 15.
Behavior4/5

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

Annotations already declare readOnlyHint true and idempotentHint true. The description adds context that it is 'Reference only' and that TFDA license/健保 給付規定 are authoritative, disclosing limitations beyond what annotations provide.

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?

The description is a single concise paragraph that front-loads purpose, then details input shapes, usage, follow-ups, out-of-scope, and disclaimers. Every sentence adds value with no redundancy.

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?

Given the complexity (four input shapes) and no output schema, the description lists return fields and explains input logic well. It also provides typical follow-ups. Slightly more detail on output structure could improve completeness, but it's adequate.

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% with good descriptions. The description adds value by explaining the auto-detection logic for the query parameter (NHI code, ATC, generic, brand), which enriches understanding beyond the schema.

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?

The description clearly states the tool searches Taiwan drugs across NHI and TFDA registries, returns specific fields, and auto-detects four input shapes. It distinguishes from siblings by listing typical follow-up tools (get_drug_rules, lookup_icd10_cm).

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

Usage Guidelines5/5

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

Explicitly says 'Use when an agent has any drug identifier and needs the canonical record for billing / SOAP / appeal context' and mentions out-of-scope topics like drug-drug interactions. Also suggests follow-ups for payment rules or diagnosis lookup.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tatsuju/opdstar-nhi-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server