Skip to main content
Glama

Is a medicine approved in a market?

lookup_medicine_evidence
Read-onlyIdempotent

Answers whether a medicine is approved, authorised, licensed or registered in a country or in the EU, or approved there for a condition, today or on a past date, and which official record settles that. Records are held for the US (the FDA's approval record on Drugs@FDA for whether a medicine is approved, and the prescribing information on DailyMed, as submitted to the FDA, for what it is approved for) and, for centrally authorised medicines, for the EU and EEA (the European Commission's product information), and each answer resting on one carries its pointer URL. For any other market, the answer names that market's competent authority and where its registration record is published, each where it is identified, and says which is not; the claim is unresolved there, or supported, never settled, by the authorisation holder's own label. For one medicine, one market and one date, the answer gives which source settles whether the medicine is registered (P1) or authorised for an indication (P2), what that source says about the claim where its content has been checked, where this market's label differs from the US and EU labels, and what is unresolved. supported_attested means the authorisation holder's own approved label, read under the attestation conditions, states the claim; it never settles it. Where that label does not state the indication, or its content has not been checked, the answer is unresolved. An unresolved answer means AlphaCitation cannot currently verify the claim from a held record; it is not evidence about the medicine's status. Every answer that does not settle carries abstention, one reason code (insufficient_evidence, authority_inaccessible, conflicting_records, stale_evidence, unsupported_claim_type, snapshot_only) with its meaning.

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": {
      "medicine": "<medicine>",
      "market": "<market>",
      "proposition": "<proposition>"
    },
    "name": "lookup_medicine_evidence"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoThe date the claim is about, YYYY-MM-DD. Defaults to today (UTC).
marketYesThe market: an ISO 3166-1 alpha-2 code (US, AE, SA, DE) or EU.
medicineYesThe brand or active substance name, exactly (for example Mounjaro or tirzepatide).
indicationNoRequired for P2: one indication from the published list. cv_risk_reduction_obesity: reducing the risk of major adverse cardiovascular events; mash_with_fibrosis: metabolic dysfunction-associated steatohepatitis (MASH) with moderate to advanced liver fibrosis; osa_with_obesity: obstructive sleep apnoea; t2dm_ckd_risk_reduction: reducing the risk of sustained eGFR decline, end-stage kidney disease and cardiovascular death; t2dm_cv_risk_reduction: reducing the risk of major adverse cardiovascular events; t2dm_glycaemic_control: glycaemic control in type 2 diabetes; weight_management: weight management.
propositionYesP1: registered or authorised in the market. P2: authorised for an indication.
populationMinAgeYearsNoOptional for P2: the youngest age the claim says the indication covers.

Output Schema

NameRequiredDescriptionDefault
notesNo
scopeYes
statusYes
recordsYes
summaryYes
relationYes
abstentionNoNull when settled. Otherwise one reason code: insufficient_evidence (route search_further): No held record settles the claim for this market and date. authority_inaccessible (route retry_later): The record that would decide the claim could not be read just now; retryAfter gives when it may be read. conflicting_records (route request_human_review): Records held disagree about the claim. stale_evidence (route search_further): The evidence held is out of date for the date asked. unsupported_claim_type (route stop): The claim is not one this service assesses: its market, proposition or indication is not supported. snapshot_only (route search_further): A past authoritative capture is held, but the current record is not confirmed.
comparisonNo
inspectionNo
unresolvedYes
indicationScopeNoWhere the regulator recorded that a use is not a separate indication, though its benefit is stated in the product information and the use is covered by an existing indication: the three apart, with the document.
competentAuthoritiesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • addedOutput schema / properties / abstention
      Added value: +{
      +  "description": "Null when settled. Otherwise one reason code: insufficient_evidence (route search_further): No held record settles the claim for this market and date. authority_inaccessible (route retry_later): The record that would decide the claim could not be read just now; retryAfter gives when it may be read. conflicting_records (route request_human_review): Records held disagree about the claim. stale_evidence (route search_further): The evidence held is out of date for the date asked. unsupported_claim_type (route stop): The claim is not one this service assesses: its market, proposition or indication is not supported. snapshot_only (route search_further): A past authoritative capture is held, but the current record is not confirmed.",
      +  "properties": {
      +    "code": {
      +      "enum": [
      +        "insufficient_evidence",
      +        "authority_inaccessible",
      +        "conflicting_records",
      +        "stale_evidence",
      +        "unsupported_claim_type",
      +        "snapshot_only"
      +      ],
      +      "type": "string"
      +    },
      +    "meaning": {
      +      "type": "string"
      +    },
      +    "route": {
      +      "enum": [
      +        "search_further",
      +        "retry_later",
      +        "request_human_review",
      +        "stop"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / indicationScope
      Added value: +{
      +  "description": "Where the regulator recorded that a use is not a separate indication, though its benefit is stated in the product information and the use is covered by an existing indication: the three apart, with the document.",
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
    • addedOutput schema / properties / inspection
      Added value: +{
      +  "type": "object"
      +}
  2. First observed

TDQS

A3.5/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint and openWorldHint=false, yet the description adds genuinely non-structured behaviour: which records are held (US, EU/EEA only), what happens elsewhere, that every non-settling answer carries an abstention with one of six reason codes, and that supported_attested never settles a claim. This is substantial beyond-annotation disclosure. It loses a point because the prose is so convoluted that the behavioural rules are harder to extract than they should be.

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

Conciseness2/5

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

The first sentence is a good front-loaded summary, but what follows is a dense block of run-on clauses such as 'each where it is identified, and says which is not' that are difficult to parse. It also enumerates the six reason codes, which the output schema field should carry, spending length on detail the agent does not need in order to select or call the tool.

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 complex regulatory-lookup tool with six parameters and an output schema, the description covers market coverage, which sources settle which proposition, and how abstention arises, which is the context an agent needs to interpret answers. Combined with a present output schema, little essential context is missing, though the ordering makes it harder to use than its coverage warrants.

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 description coverage is 100%, so the schema already defines market, medicine, date, proposition and indication, including the enumerated indications. The description adds some contextual meaning, notably that only the US and EU/EEA have held records and that P1/P2 map to registration versus indication-level authorisation, but this is largely restating what the schema enumerations convey. Baseline 3 applies.

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?

The opening sentence states a specific verb and resource: it answers whether a medicine is approved, authorised, licensed or registered in a country or the EU, and whether that approval is condition-specific or date-specific. That is far more precise than a restatement of the name. It does not differentiate itself from the sibling lookup_precedent_ruling, leaving the agent to infer the boundary.

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?

Usage is implied through the query shape ('For one medicine, one market and one date') and through the explanation of what happens in markets without a held record. There is no explicit when-to-use statement, no when-not-to-use, and no named alternative; the agent must infer the boundary from the described output behaviour rather than from guidance.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.