Skip to main content
Glama
Sign In

Tga Artg

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Artg Search

artg_search
Read-onlyIdempotent

Search the Australian Register of Therapeutic Goods (ARTG) — every medicine, biological and medical device approved for supply in Australia — by product name, active ingredient, sponsor, or manufacturer. Returns each entry's ARTG ID, entry type (e.g. "Medicine Registered", "Medicine Listed"), sponsor, active ingredients, status, and links to its Product Information (PI, prescriber label) and Consumer Medicine Information (CMI, patient leaflet) documents. Answers "is X approved in Australia", "which Australian products contain ibuprofen", "who sponsors X in Australia". This calls the TGA's own JSON web service directly (data.tga.gov.au) rather than the interactive ARTG Search web tool. Paged: the response carries total, has_more and next_offset — pass offset to fetch the next page. Example: artg_search({ ingredient: "paracetamol" }); artg_search({ ingredient: "amoxicillin", offset: 100 }). Keyless.

Input Schema

NameRequiredDescriptionDefault
nameNoProduct/trade name, e.g. "Panadol"
limitNoMax entries to return (default 25, max 100)
queryNoAlias of name, accepted because routers and callers commonly send "query". Prefer name or ingredient.
offsetNoNumber of matching entries to skip (0-based). Use next_offset from the previous response to page.
productNoProduct name fragment (device/product-level, distinct from name)
sponsorNoSponsor (marketing-authorisation holder) name, e.g. "Pfizer"
entry_typeNoRestrict to an ARTG entry type; matches its start, e.g. "Medicine", "Medicine Registered", "Medicine Listed", "Biological", "Medical Device"
ingredientNoActive ingredient, e.g. "paracetamol", "ibuprofen"
manufacturerNoManufacturer name

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / query
      Added value: +{
+  "description": "Alias of name, accepted because routers and callers commonly send \"query\". Prefer name or ingredient.",
+  "type": "string"
+}
  2. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, openWorld), and the description adds genuinely new context: no API key required, the upstream source is data.tga.gov.au rather than the interactive web tool, and pagination uses total/has_more/next_offset with offset as the cursor. Rate limits and failure behaviour are unstated, keeping it off a 5.

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

Conciseness4/5

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

Front-loaded with the resource and the return shape, then usage questions, then pagination mechanics. Slightly long and the inline example calls repeat what the schema examples already show, but no sentence is filler.

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?

For a nine-parameter, no-output-schema tool the description does the heavy lifting well: it lists return fields and the pagination envelope that the schema cannot express. The remaining gap is sibling disambiguation against artg_entry/artg_list/artg_recent, which matters given the toolset's density.

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

Parameters3/5

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

Schema coverage is 100%, so the schema already documents all nine parameters and the baseline is 3. The description reinforces ingredient and offset usage with example calls, but it does not resolve the genuinely confusing overlap between name, product and the query alias, which is the one thing the schema handles only thinly.

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

Purpose4/5

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

Specific verb ('Search') plus a named resource with an expanded definition, and it enumerates both the search keys (name, ingredient, sponsor, manufacturer) and the returned fields. It never differentiates itself from the obvious siblings artg_entry, artg_list and artg_recent, so an agent cannot tell from the description alone which of those four to pick.

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

Usage Guidelines4/5

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

Gives concrete question shapes it answers ('is X approved in Australia', 'which Australian products contain ibuprofen', 'who sponsors X in Australia'), which effectively tells the agent when to reach for it. No exclusions or named alternatives are stated, and the distinction from artg_entry (presumably single-entry lookup) is left implicit.

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

All Tga Artg toolsInspect
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