Skip to main content
Glama

ILO Labour Statistics (ILOSTAT)

by io.github.SidneyBissoli

Deep Research Document

fetch
Read-onlyIdempotent

Returns the full document for an id obtained from search, as { id, title, text, url, metadata }: text is the readable content (Markdown) and url the canonical public page to cite.

Companion of search in the OpenAI Deep Research contract, over the ILOSTAT labour statistics (≈1,200 SDMX dataflows: employment, unemployment, wages, working time, informality, SDG labour indicators) catalog. Only ids returned by search are valid; an unknown id returns an error. The ilo_* tools remain the tools for data queries.

Behavior: read-only and idempotent — a live GET against the public source when the document needs it.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesIdentifier of a document returned by `search`

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesUnique identifier of the document on this server; what `fetch` takes
urlYesCanonical public URL of the document — ChatGPT's citation depends on it
textYesFull readable content of the document (Markdown)
titleYesHuman-readable title of the document
metadataNoAdditional key/value pairs about the document (kind, source, period…)
provenanceYes
attributionYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. First observed

TDQS

A4.9/5.0
Behavior5/5

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

The description adds meaningful behavior beyond the annotations: it is read-only and idempotent, performs a live GET against the public source when needed, and returns an error for unknown ids. It also discloses the return shape. This complements, rather than contradicts, the annotations.

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?

The description is well-structured: the core function and return shape come first, followed by context and behavior. It is concise enough that every sentence adds useful information, and it avoids repeating the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with an output schema and safety annotations, the description covers everything needed: source of ids, return format, error behavior, read-only nature, and relationship to sibling tools. Nothing critical is missing for correct invocation.

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 the baseline is 3. The description adds extra semantic value by specifying that the id must come from `search`, that only such ids are valid, and that unknown ids produce errors—details not present in the schema's parameter description.

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 a specific action ('Returns the full document') and names the resource (document identified by an id from `search`). It also distinguishes itself from siblings by explicitly separating the `ilo_*` data-query tools from this document-fetch contract.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly states when to use the tool: after obtaining an id from `search`, and only ids from `search` are valid. It also provides an exclusion by reserving `ilo_*` tools for data queries, so an agent knows this is not for statistical data retrieval.

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

All ILO Labour Statistics (ILOSTAT) 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

A4.6/5.0
Disambiguation4/5

The ilo_* tools are clearly role-separated: get data, inspect metadata, list dimension codes, and search indicators. The only real ambiguity is between `search` and `ilo_search_indicators`, which both query the same catalogue, though the descriptions clarify that one returns documents for `fetch` while the other returns dataflow ids for data queries.

Naming Consistency4/5

Most tools follow a predictable `ilo_<verb>_<object>` pattern: get_data, get_indicator_metadata, list_dimension_values, search_indicators. `fetch` and `search` break that pattern, but this is an explicitly forced adapter to the OpenAI Deep Research contract rather than random inconsistency.

Tool Count5/5

Six tools are well-scoped for the stated domain: the search/fetch pair handles document retrieval, and the four `ilo_*` tools cover indicator discovery, metadata inspection, dimension-value lookup, and raw statistical data extraction. No tool feels redundant or unnecessary.

Completeness4/5

The set covers the full workflow from finding an indicator dataflow, inspecting its structure, listing valid codelist values, and retrieving raw data. A minor gap is that `ilo_list_dimension_values` suggests using `search` to resolve a name like 'Brazil' to a code, but `search` actually returns catalogue documents rather than codelist codes, so name-to-code resolution lacks a direct tool.

Resources