worldgdp.org GDP nowcasts

get_sectors

World Sector Activity Index: monthly readings on the 50 line (50 = as many firms report rising as falling) by GICS-aligned sector, industry group, industry and sub-industry, for the World, regions (EUROPE, NAMERICA) and countries (EU, EA, US, DE, FR, IT, ES, ...). Built from national business surveys (European Commission NACE subsectors; US Census Business Trends and Outlook Survey) through worldgdp.org's own classification crosswalk. Measures: out (output), new (new orders), emp (employment), fut (future activity), px (prices charged). Default readings are bias-adjusted (each series centred on its own long-run average so countries compare like for like); set adjusted=false for raw survey readings. Give node (GICS code like '45' or '4530', or a name fragment) to rank its children and get its history; omit for the 11 sectors.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_sectors"
  }
}

Input Schema

Name	Required	Description	Default
`geo`	No	WORLD (default), EUROPE, NAMERICA, EU, EA, US or a European country code (DE, FR, IT, ES, NL, PL, ...)
`node`	No	GICS-aligned code ('20', '2010', '201060', '20106020') or name fragment ('semiconductors', 'banks'); omit for all sectors
`months`	No	Months of history for the node (output; long history at sector and industry-group level)
`measure`	No		out
`adjusted`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedNov 4, 2026

addedInput schema / properties / adjusted

Added value: +{
+  "default": true,
+  "type": "boolean"
+}

changedInput schema / properties / geo / description

Previous value: -"EC country code: EA (euro area, default), EU, DE, FR, IT, ES, NL, PL, AT, BE, SE, IE, EL (Greece), PT, FI, CZ, HU, RO, TR, ..."New value: +"WORLD (default), EUROPE, NAMERICA, EU, EA, US or a European country code (DE, FR, IT, ES, NL, PL, ...)"

changedInput schema / properties / months / description

Previous value: -"Months of history when a sector is given (latest last)"New value: +"Months of history for the node (output; long history at sector and industry-group level)"

addedInput schema / properties / node

Added value: +{
+  "description": "GICS-aligned code ('20', '2010', '201060', '20106020') or name fragment ('semiconductors', 'banks'); omit for all sectors",
+  "type": "string"
+}

removedInput schema / properties / sector

Removed value: -{
-  "description": "Sector name or fragment, e.g. 'Chemicals', 'Software', 'Autos', 'Banks', 'all' for the all-sector composite; omit for the ranking",
-  "type": "string"
-}

AddedNov 3, 2026

TDQS

A4.3/5.0

Behavior4/5

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

With no annotations, the description carries the load and does well: it discloses the bias-adjustment default and what adjusted=false returns, the underlying data sources and crosswalk, and the measure codes' meaning. It does not cover permissions, rate limits, or response shape, but the methodological behavior an agent most needs is disclosed.

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 identity of the index, then scope, then data provenance, then measures, then parameter behaviors; every sentence carries information. It is a dense single block rather than a structured list, and the provenance/crosswalk sentence is helpful context rather than essential, so it stops just short of maximal efficiency.

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 five-parameter tool with no output schema and no annotations, the description covers scope, measures, adjustment, node resolution behavior, and history depth. What remains thin is interaction between geo and node and what happens on an unresolved node fragment, but the essentials for a correct call are present.

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 60%, and the description compensates for the uncovered parts: it expands each measure abbreviation (out=output, new=new orders, emp=employment, fut=future activity, px=prices charged) and explains the bias-adjustment semantics of adjusted, neither of which has a schema description. Node semantics (ranking children, name fragments, the '45'/'4530' code forms) are reinforced with behavior the schema does not state.

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 names a specific resource (World Sector Activity Index monthly readings), states the threshold convention (50 line = balanced rising/falling), and enumerates the full dimension set: GICS-aligned sector/industry group/industry/sub-industry across geographies and five measures. An agent knows exactly what data comes back and at what granularity, which clearly separates it from siblings like get_nowcast or get_aggregate.

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?

It gives concrete operating guidance for the key choice: pass node to rank its children and retrieve history, omit it to get the 11 sectors, and set adjusted=false for raw readings. What it lacks is explicit routing against siblings (when to prefer get_us_industries or get_aggregate) and any stated exclusions.

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

All worldgdp.org GDP nowcasts tools Inspect

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

Need Help?