Skip to main content
Glama

get_indicator

Look up a Taiwan NHI audit indicator to get its threshold, applicable drugs/diagnoses, and compliance meaning. Understand which prescriptions trigger NHI audits.

Instructions

Look up a Taiwan NHI audit indicator (e.g. '008', '014', '027', 'P043') — threshold, applicable drugs/diagnoses, and compliance meaning. These are the indicators the NHI uses to flag overprescription and trigger audits. Curated by OPDSTAR (https://opdstar.com).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
codeYesIndicator code, e.g. '008' (antibiotic for URI), 'P043' (duration limit)

Implementation Reference

  • Tool definition & input schema for 'get_indicator' — defines the tool name, description, and that it requires a 'code' string parameter.
    export const GET_INDICATOR_DEF = {
      name: 'get_indicator',
      description:
        "Look up a Taiwan NHI audit indicator (e.g. '008', '014', '027', 'P043') — threshold, applicable drugs/diagnoses, and compliance meaning. These are the indicators the NHI uses to flag overprescription and trigger audits. Curated by OPDSTAR (https://opdstar.com).",
      inputSchema: {
        type: 'object',
        properties: {
          code: {
            type: 'string',
            description: "Indicator code, e.g. '008' (antibiotic for URI), 'P043' (duration limit)",
          },
        },
        required: ['code'],
      },
    } as const;
  • Handler that executes the 'get_indicator' tool — validates the 'code' param, then calls client.get('/indicator', { code }) to fetch the NHI audit indicator data.
    export async function runGetIndicator(
      client: OpdstarClient,
      args: GetIndicatorArgs
    ): Promise<IndicatorResult> {
      if (!args || typeof args.code !== 'string') {
        throw new Error('Missing required parameter: code');
      }
      return (await client.get('/indicator', { code: args.code.trim() })) as IndicatorResult;
    }
  • src/index.ts:47-52 (registration)
    Registration of 'get_indicator' in the ListTools handler, exposing GET_INDICATOR_DEF as one of the available tools.
    server.setRequestHandler(ListToolsRequestSchema, async () => ({
      tools: [
        LOOKUP_REJECTION_CODE_DEF,
        GET_PROCEDURES_FOR_ICD_DEF,
        GET_INDICATOR_DEF,
        SEARCH_NHI_WIKI_DEF,
  • Dispatcher switch-case that routes 'get_indicator' requests to runGetIndicator() at runtime.
    case 'get_indicator':
      result = await runGetIndicator(client, args as never);
      break;
  • TypeScript interface defining the argument shape for the get_indicator tool (code string).
    export interface GetIndicatorArgs {
      code: string;
    }
    
    export async function runGetIndicator(
      client: OpdstarClient,
      args: GetIndicatorArgs
    ): Promise<IndicatorResult> {
      if (!args || typeof args.code !== 'string') {
        throw new Error('Missing required parameter: code');
      }
      return (await client.get('/indicator', { code: args.code.trim() })) as IndicatorResult;
    }
Behavior3/5

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

The description implies a read-only lookup (no side effects) and describes return content, but with no annotations, it does not explicitly state safety, auth needs, or error behaviors. The curation note adds context but not behavioral constraints.

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 tightly convey purpose, examples, content, and source. No unnecessary words. Front-loaded with key information.

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?

The description explains what the tool returns (threshold, drugs, diagnoses, compliance meaning) and mentions the source (OPDSTAR). Lacks mention of error handling or missing codes, but adequate for a simple lookup.

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 a description for the 'code' parameter. The description adds valuable examples (e.g., '008' for antibiotic URI, 'P043' for duration limit) that clarify acceptable input, surpassing the schema alone.

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 looks up Taiwan NHI audit indicators and provides concrete examples like '008' and 'P043'. It distinguishes the resource (indicators) from sibling tools that handle procedures, rejection codes, or wiki searches.

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 description implies the tool is for looking up indicator details but does not explicitly state when to use it over alternatives or exclude other scenarios. No guidance on when not to use it.

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