Official economic statistics for AI agents: GDP, inflation, trade and debt for 150+ countries.
Scored across 4 tools
The four tools split cleanly along a search → inspect → retrieve → metadata workflow, and descriptions explicitly differentiate search_catalog (cards) from get_series (values). The only overlap is get_dataset vs inspect_dataset, both returning dataset-level metadata, though get_dataset is 'full metadata' while inspect_dataset adds dimensions and sample values.
All names follow a strict verb_noun snake_case pattern: get_dataset, get_series, inspect_dataset, search_catalog. Verbs are accurate and the dataset/series vs catalog distinction is reflected consistently.
Four tools is a lean but coherent surface for a read-only statistical data access server, and each earns its place in the discover-then-fetch flow. It sits slightly under the ideal range, with no batch or multi-country retrieval tool.
The surface covers the core read lifecycle: find datasets (search_catalog), vet them (inspect_dataset), read metadata (get_dataset), and pull time series (get_series). Minor gaps exist—no multi-country comparison or bulk series retrieval—but agents can work around these by repeated calls.
Full metadata for one dataset: description, source, period range, dimension labels, default view and covered countries.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Dataset id from search_catalog. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is fully covered elsewhere. The description's only added value is disclosing what the metadata contains, which is useful but modest; it does not say whether data points are included versus the separate get_series tool.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
One front-loaded sentence: the verb and resource come first, followed by a dense, comma-separated list of contents with no filler or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description does the job of enumerating return contents, and annotations cover safety and idempotency. It lacks any statement of when this is preferable to inspect_dataset or get_series, so it is not fully complete for selecting among the siblings.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
There is a single parameter with 100% schema description coverage, and that schema text ('Dataset id from search_catalog') actually carries the more useful context. The description adds nothing about the id parameter, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb+resource (get full metadata for one dataset) and enumerates the returned fields (description, source, period range, dimension labels, default view, covered countries). It does not explicitly differentiate from the sibling inspect_dataset, which plausibly overlaps in scope, so it falls short of a 5.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description gives no when-to-use guidance and names no alternatives, even though inspect_dataset appears to be a close sibling. The only routing hint ('Dataset id from search_catalog') lives in the schema, not the description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Time series values for one country from a dataset (oldest first). Optionally pick a series by exact dimension values (from inspect_dataset) and a start period such as 2015, Q1/2015 or 01/2015.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Dataset id from search_catalog. | |
| dim1 | No | Optional exact value of dimension 1. | |
| dim2 | No | Optional exact value of dimension 2. | |
| dim3 | No | Optional exact value of dimension 3. | |
| dim4 | No | Optional exact value of dimension 4. | |
| country | No | Country, e.g. 'Poland'. Defaults to the dataset's default country. | |
| max_points | No | Max points, most recent kept (default 200). | |
| period_from | No | Optional first period to include, e.g. '2015'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds useful behavior beyond that: chronological ordering, default-country fallback, and the default point cap with 'most recent kept' retention policy. It stops short of return-format or truncation signalling, but adds real value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two tight sentences; the core purpose and ordering constraint are front-loaded, and the optional-selection guidance follows without padding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
No output schema exists, so the description carries the burden of return semantics; it discloses ordering and the max_points retention rule, which is the key consumer-facing detail. A note on what happens when no exact series matches would make it fully self-contained.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
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 goes beyond the schema by giving concrete period syntax examples (2015, Q1/2015, 01/2015) where the schema only shows '2015', and by explaining that dimension values come from inspect_dataset.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Time series values for one country from a dataset') plus scope (single country) and ordering (oldest first). This is clearly distinguishable from the sibling tools get_dataset, inspect_dataset, and search_catalog.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It routes the agent to inspect_dataset for obtaining dimension values and explains the optional series-selection path and start-period usage. It doesn't explicitly state when to prefer this over get_dataset, but the workflow context is clear.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Show one dataset's dimensions, default series and the latest few values for a country. Use after search_catalog to check the dataset fits before pulling the full series.
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Dataset id from search_catalog. | |
| country | No | Optional country, e.g. 'France'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, idempotentHint=true, destructiveHint=false, so safety is covered structurally. The description adds the non-obvious behavioral trait that this returns only a preview (dimensions + "latest few values") rather than the full data, which is real context beyond the annotations. It doesn't mention rate limits or sampling window specifics, so not 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.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences with no waste: sentence one lists outputs, sentence two gives placement and purpose. Front-loaded and appropriately sized for a two-parameter read tool.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no output schema, the description carries the burden of describing returns and does so reasonably (dimensions, default series, latest few values). It is slightly incomplete on how many values constitute "latest few" and on behavior when country is omitted, but it is adequate for a read-only preview tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so both id and country are already documented, giving a baseline of 3. The phrase "for a country" reinforces that country scopes the sample, but adds no syntax or default behavior beyond the schema's "Optional country, e.g. 'France'."
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb ("Show") and resource (one dataset) and enumerates what is surfaced: dimensions, default series, and latest values. It implicitly separates itself from get_series by framing it as a fit-check before "pulling the full series," but never names get_dataset or get_series directly, so sibling differentiation is partial.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Gives explicit sequencing guidance ("Use after search_catalog") and the purpose condition ("check the dataset fits before pulling the full series"), which routes the agent well. It stops short of naming when-not-to-use or the explicit alternative tool for the full pull.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Find official economy datasets (Eurostat, OECD, World Bank, IMF, WHO, national statistics offices). Use first to get dataset ids. Optional country and source filters. Returns dataset cards, not values.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Max results (default 8). | |
| query | Yes | What to find, e.g. 'unemployment rate' or 'GDP per capita'. | |
| country | No | Optional country name to prefer datasets covering it, e.g. 'Germany'. | |
| source_name | No | Optional source, e.g. 'Eurostat', 'OECD', 'World Bank', 'IMF'. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds real behavioral value not in annotations: it discloses the return shape ('dataset cards, not values') and that the search returns ids rather than data, which matters because there is no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Four short sentences, front-loaded with purpose and routing guidance before filter notes and the return-value caveat. Every sentence carries information; nothing is padding.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a read-only search with no output schema, the description covers what it returns, when to call it, and what the filters do. It does not explain result ordering, pagination behavior, or what happens when no datasets match, which are minor gaps given the annotations already establish the operation is safe and idempotent.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so every parameter (query, country, source_name, limit) is already documented in the schema with examples. The description only restates that country and source filters are optional, adding no syntax, format, or matching-behavior detail beyond the schema, so the baseline 3 applies.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
States a specific verb and resource ('Find official economy datasets') and names the actual catalogues it covers. The line 'Returns dataset cards, not values' plus 'Use first to get dataset ids' cleanly separates it from value-oriented siblings like get_series and get_dataset.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
'Use first to get dataset ids' gives explicit ordering guidance that tells the agent this is the entry point before get_dataset/inspect_dataset. It stops short of naming a sibling as an alternative for a specific condition, so it is clear context rather than full when/when-not routing.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
get_datasetget_seriesinspect_datasetsearch_catalogOfficial statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries.
Macro data for AI agents: GDP, inflation, unemployment and more (World Bank, US BLS). No keys.
Macro data for AI agents: GDP, inflation, unemployment and more (World Bank, US BLS). No keys.
Labour market statistics for AI agents: unemployment, employment and wages for 150+ countries.
Add one secure layer between your agents and this server.
