Skip to main content
Glama

Worldbank Poverty

by io.github.pipeworx-io

Get Poverty

get_poverty
Read-onlyIdempotent

Official World Bank poverty & inequality estimates for a country (or all countries). Returns poverty headcount, poverty gap, poverty severity, Gini, mean & median welfare (income or consumption, $/day in 2017 PPP), income deciles, and population in poverty. Use povline to pick the international line: 2.15 (extreme poverty), 3.65 (lower-middle-income), 6.85 (upper-middle-income).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
yearNoReporting year (e.g. "2020") or "all" for the full time series. Default "all".
countryNoISO3 country code (e.g. "BRA", "IND", "NGA") or "all" for every country. Default "all".
povlineNoPoverty line in $/day (2017 PPP). Common values: 2.15, 3.65, 6.85. Default 2.15.
fill_gapsNoIf true, interpolate/extrapolate estimates for years without a survey. Default false (survey years only).

TDQS

A3.6/5.0
Behavior3/5

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

Annotations already declare the tool as read-only, open-world, idempotent, and non-destructive. The description adds context about the data source (World Bank) and the metrics returned, but does not disclose behavioral traits beyond what annotations provide. It is consistent with annotations.

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?

The description is three sentences long, concise, and front-loaded with purpose. It efficiently lists returned metrics and parameter guidance. There is no filler, though the structure could be slightly improved by separating the return list from parameter details.

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?

Given no output schema, the description adequately explains return values (poverty headcount, Gini, etc.) and parameter defaults (year, country, fill_gaps). It covers the essential context for a query tool. The only missing element is explicit mention that all parameters are optional, but schema defaults compensate.

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%, so baseline is 3. The description adds significant value for the 'povline' parameter by explicitly mapping values to income classifications (2.15 for extreme poverty, etc.), which is not fully covered by the schema's 'Common values' note. Other parameters add minimal extra meaning, but the povline enrichment justifies a 4.

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 description clearly identifies the tool's purpose: retrieving official World Bank poverty and inequality estimates for a country or all countries. It specifies the returned metrics (headcount, gap, severity, Gini, etc.) and distinguishes itself from the sibling tool 'get_poverty_regional' by focusing on national-level data, though it does not explicitly name the sibling.

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 advises using the 'povline' parameter with three specific values and explains what each represents. However, it does not provide guidance on when to use this tool versus alternatives like 'get_poverty_regional', nor does it mention prerequisites or exclusions. Usage is implied but not explicit.

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

All Worldbank Poverty toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.6/5.0
Disambiguation2/5

Many tools have overlapping purposes, especially the pipeworx family (ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, deep_research) which all route to the same data sources. Additionally, the server includes unrelated meta-tools (remember/recall/forget, generate_llms_txt, pipeworx_feedback) that have no clear boundaries with the poverty data tools, and betting tools that seem out of place. The core poverty tools (get_poverty, get_poverty_regional, list_reference) are distinct, but the rest creates significant confusion.

Naming Consistency2/5

Tool names are a mix of styles: some use snake_case (get_poverty, list_reference, suggest_questions), some use camelCase (ask_pipeworx, bet_research, scan_competitor_ai_presence), and others are single words (recall, remember, forget, subscribe). The naming pattern is highly inconsistent, making it hard to predict related tool names.

Tool Count2/5

With 34 tools, this server is heavily overloaded for a 'Worldbank Poverty' server. The majority of tools are unrelated to poverty (Polymarket betting, AI marketing, npm package checks, LLM visibility). The core poverty functionality could be served by 3-5 tools, but instead the server includes dozens of extra tools from a generic data platform, making the count inappropriate for the stated domain.

Completeness4/5

For the poverty data domain, the tool surface is actually quite complete: get_poverty for country-level data, get_poverty_regional for aggregations, and list_reference for metadata. The only minor gap is a lack of a tool for comparing poverty across countries directly, but that is easy to work around by calling get_poverty multiple times. The extra meta-tools do not affect poverty data completeness.

Resources