Skip to main content
Glama

Wikidata

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Get Entities

get_entities
Read-onlyIdempotent

Batch version of get_entity — resolve up to 50 Wikidata Q-ids in ONE call instead of looping single get_entity calls. Same fields as get_entity per entity (labels, descriptions, aliases, claims, sitelinks, revision info), keyed by Q-id. Any id that does not resolve (bad format, deleted, or genuinely unknown) is reported in "not_found" rather than failing the whole batch — the other ids still resolve. Pass "language" (comma/pipe-joined for several) the same as get_entity to get multilingual labels for every entity in the batch.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
idsYesWikidata Q-ids to resolve, up to 50 — either an array of strings (e.g. ["Q162887","Q1326165","Q3493773"]) or a single comma/pipe-joined string (e.g. "Q162887,Q1326165,Q3493773").
languageNoLanguage code(s) for labels/descriptions/aliases — a single code (e.g. "ka") or a comma/pipe-joined list to compare several at once (e.g. "ka,ru,en"), which returns every requested language's label side by side in one call — the shape needed to decide whether two records in different languages describe the same entity. Default "en". Falls back to "en", then to Wikidata's language-neutral "mul" label, for any requested language the entity has no label in — Q42 (Douglas Adams) has no English label at all, only a "mul" one. When the name came from "mul" it appears under a "mul" key in the labels map, so you can tell where it came from.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "ids": [
-      "Q162887",
-      "Q1326165",
-      "Q3493773"
-    ]
-  },
-  {
-    "ids": "Q162887,Q1326165,Q3493773",
-    "language": "ka,en"
-  }
-]New value: +[
+  {
+    "ids": [
+      "Q162887",
+      "Q1326165",
+      "Q3493773"
+    ]
+  },
+  {
+    "ids": "Q162887,Q1326165,Q3493773",
+    "language": "ka,en"
+  },
+  {
+    "ids": [
+      "Q162887",
+      "Q1326165",
+      "Q3493773",
+      "Q42",
+      "Q90"
+    ]
+  }
+]
    • changedInput schema / properties / language / description
      Previous value: -"Language code(s) for labels/descriptions/aliases — a single code (e.g. \"ka\") or a comma/pipe-joined list to compare several at once (e.g. \"ka,ru,en\"), which returns every requested language's label side by side in one call — the shape needed to decide whether two records in different languages describe the same entity. Default \"en\". Falls back to \"en\" for any requested language the entity has no label in."New value: +"Language code(s) for labels/descriptions/aliases — a single code (e.g. \"ka\") or a comma/pipe-joined list to compare several at once (e.g. \"ka,ru,en\"), which returns every requested language's label side by side in one call — the shape needed to decide whether two records in different languages describe the same entity. Default \"en\". Falls back to \"en\", then to Wikidata's language-neutral \"mul\" label, for any requested language the entity has no label in — Q42 (Douglas Adams) has no English label at all, only a \"mul\" one. When the name came from \"mul\" it appears under a \"mul\" key in the labels map, so you can tell where it came from."
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already declare readOnlyHint/openWorldHint/idempotentHint, and the description adds genuinely useful behavior: unknown or malformed IDs are returned in not_found rather than failing the whole call, and multilingual labels fall back with a 'mul' key. This goes well beyond the schema.

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 front-loaded with the single most important fact (batch vs single), then efficiently covers fields, partial failures, and the language parameter. Every sentence carries meaning; no filler.

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?

It covers success shape (same fields as get_entity), partial failure (not_found), and language behavior. It never explicitly explains pagination, rate limits, or handling over 50 IDs, but for a batch read tool with no output schema, the essential usage contract is well covered.

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?

The input schema already documents ids (array or comma-joined string) and language (including multi-language joining and fallback) in detail. The description repeats 'same as get_entity' and adds the not_found/fields context, but because coverage is high, it adds little new parameter-level meaning.

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 opens with a specific verb and relationship: 'Batch version of get_entity' — resolving up to 50 Q-ids in ONE call. It explicitly names the single-entity sibling and distinguishes itself from looping over get_entity, so intent is unambiguous.

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 clearly instructs when to use the tool (multiple Q-ids in one call, avoiding loops of get_entity) and how to pass language. It doesn't mention alternatives like search or resolve_entity, but the batch-vs-single distinction is enough to avoid confusion with its direct sibling.

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

All Wikidata toolsInspect
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