Skip to main content
Glama

Podziemie Analityczne

Get neighbours

podziemie_get_neighbours
Read-onlyIdempotent

Every series to walk to from one series, as the dependency map on the site draws it: stored links with their direction and evidence (the stored basis), other measures of the same concept, the same measure at a neighbouring place or for the whole country, and other measures at the same place. With familyTable it also returns the family table its site page shows: every member's latest value, unit and change, and, where the family compares with Polska, the gap to Polska and the place. Call it again on a neighbour to walk on. Navigation hints, not proof of a cause.

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": "podziemie_get_neighbours"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoPublic series id: a slug or <dataset>/<dimension>=<code>.
slugNoSeries id, e.g. "inflacja-cpi" (from podziemie_search_series).
limitNoAt most this many neighbours, in the map's order; default every one.
relationsNoOnly these relations; default every one. variant: another measure of the same concept; family: the same measure one step away (a neighbouring place, the whole country, another group); place: another measure at the same place; the rest are stored links.
familyTableNoAlso return the family table the series' page shows: each member's latest value, unit and change, and the gap to Polska and the place where the family compares with Polska. It reads up to about a hundred series, so it is off by default.

Output Schema

NameRequiredDescriptionDefault
idNo
nameNo
slugYes
labelNo
caveatNo
familyNo
statusYes
pageUrlNo
neighboursNo
suggestionsNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description adds value beyond them: familyTable 'reads up to about a hundred series, so it is off by default' is a real cost/latency disclosure that explains the default, and 'Navigation hints, not proof of a cause' sets epistemic expectations for the link evidence. It does not describe pagination or how the map's order is determined, but the essential behavioral context is present.

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 core purpose is front-loaded in the opening clause, and the second sentence covers the familyTable option and the caveat. It is dense and clause-heavy, with a long parenthetical list of relation types, but nearly every clause carries information an agent needs. Slightly tighter phrasing would help readability.

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?

All parameters are optional and an output schema exists, so the description does not need to document return values; it nonetheless sketches what familyTable returns. For a read-only graph-walk tool this is close to sufficient. The remaining hole is the relationship to the similarly named related-series sibling, which an agent must resolve on its own.

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 coverage is 100%, so each parameter including the relations enum is already documented in the schema. The description reinforces relations semantics and the familyTable cost rationale, but largely restates what the schema says rather than adding new syntax or format detail. Baseline 3 is appropriate.

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?

Names a specific verb-plus-resource: the series reachable from one series per the site's dependency map, and enumerates the relation classes (stored links, same concept, neighbouring place, same place). That is far more than a restatement of the title. The gap is sibling differentiation: it never distinguishes itself from podziemie_related_series or podziemie_get_series, which an agent could plausibly pick instead.

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?

Gives one concrete usage pattern: 'Call it again on a neighbour to walk on,' which tells the agent this is an iterative graph-walk tool. It also warns the output is 'Navigation hints, not proof of a cause.' There is no explicit when-not, no stated alternative for simpler lookups, and no prerequisite note (e.g. obtaining an id from podziemie_search_series, though the schema mentions that).

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