Skip to main content
Glama

Agent Master Data

Get Reference Data

get_reference_data
Read-onlyIdempotent

Paid x402 tool. Get governed public reference data and controlled vocabulary values such as country, currency, unit of measure, industry, status, category, or code mappings. Returns codes, labels, definitions, validity dates, mappings, provenance, and version. Price ID: price.reference.v1.

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": {
      "domain": "<domain>"
    },
    "name": "get_reference_data"
  }
}

Input Schema

NameRequiredDescriptionDefault
codesNoExact codes wanted. Set membership, never a substring match; omit it to narrow nothing.
limitNoPage size, applied after query, codes, and validity have narrowed the list. For mitre-cwe the maximum is 125.
queryNoOptional code or label search: a case-insensitive substring match against a value's code OR its label. Omit it to match every value.
cursorNoOpaque continuation cursor from a prior identical request. Bound to the operation, the normalized request, and the data_version it paged.
domainYesReference-data domain identifier, as get_master_data_schema names it.
localeNoLanguage tag echoed on every served value and in the answer. Labels are served exactly as the snapshot stores them; there is no translation layer. For mitre-cwe, the tag may contain at most 64 ASCII bytes.en
valid_atNoThe instant to evaluate each value's validity interval at. Defaults to the request clock. A value whose source DECLARES its interval is active when valid_from <= valid_at < valid_to, an absent or null bound open on its side. A value whose source states no interval at all is neither: it is served active: null and carries the reference_value_validity_unknown warning.
include_inactiveNoWhether values declared inactive at valid_at are served. A value whose source states no validity interval is always served, flagged active: null beside the reference_value_validity_unknown warning. False excludes values declared inactive; true serves them flagged active: false beside the reference_value_inactive warning, so an intentionally excluded value is distinguishable from an accidental match.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / include_inactive / description
      Previous value: -"Whether values not KNOWN to be active at valid_at are served. False excludes them; true serves them flagged - active: false for a value declared inactive, beside the reference_value_inactive warning, and active: null for one whose source states no validity interval, beside reference_value_validity_unknown - so an intentionally excluded value is distinguishable from an accidental match. Either warning is carried when such a value is WITHHELD too, so the omission is never silent."New value: +"Whether values declared inactive at valid_at are served. A value whose source states no validity interval is always served, flagged active: null beside the reference_value_validity_unknown warning. False excludes values declared inactive; true serves them flagged active: false beside the reference_value_inactive warning, so an intentionally excluded value is distinguishable from an accidental match."
  2. Changed2 schema fields changed
    • changedInput schema / properties / limit / description
      Previous value: -"Page size, applied after query, codes, and validity have narrowed the list."New value: +"Page size, applied after query, codes, and validity have narrowed the list. For mitre-cwe the maximum is 125."
    • changedInput schema / properties / locale / description
      Previous value: -"Language tag echoed on every served value and in the answer. Labels are served exactly as the snapshot stores them; there is no translation layer."New value: +"Language tag echoed on every served value and in the answer. Labels are served exactly as the snapshot stores them; there is no translation layer. For mitre-cwe, the tag may contain at most 64 ASCII bytes."
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare read-only, idempotent, non-destructive, closed-world behavior, so the bar is lower. The description still adds genuinely new behavioral facts: this is a paid x402 tool with Price ID price.reference.v1, and the response carries provenance, version, and validity dates. It doesn't mention cost magnitude or failure modes for billing, which keeps it short of 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.

Conciseness5/5

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

Three tightly packed sentences with the payment model and price ID front-loaded, followed by the resource scope and the returned fields. Every clause is doing work and nothing is repeated.

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 steps in to enumerate return contents (codes, labels, definitions, validity dates, mappings, provenance, version), which is exactly what the agent needs. What remains unstated is pagination behavior and the cost magnitude behind the price ID, minor gaps given the 100%-documented input schema.

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% and every parameter (codes, query, limit, cursor, locale, valid_at, include_inactive) is documented in detail in the schema itself, so baseline 3 applies. The description contributes no parameter-level meaning beyond what the schema already says.

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?

States a specific verb and resource ('Get governed public reference data and controlled vocabulary values') and enumerates concrete domains (country, currency, unit of measure, industry, status, category, code mappings). An agent can tell this is a vocabulary/code-list lookup rather than a master-data entity tool, though the description never explicitly contrasts it with siblings like search_master_data or get_master_data_golden_record.

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 only implied: the domain parameter points at 'get_master_data_schema' for naming domains, which is a useful routing hint, but there is no statement of when to prefer this tool over search_master_data or get_master_data_golden_record, and no exclusions. An agent must infer that this is for code lists rather than records.

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.

Resources