Opentargets

Search

search

Read-onlyIdempotent

"Find [disease / drug / gene target]" / "Open Targets lookup for [name]" / "what's the Open Targets ID for [X]" — text search across diseases, drug targets, and drugs in the Open Targets Platform (the leading drug-discovery knowledge graph). Returns ranked matches with their canonical IDs (ENSG... for targets, EFO_... for diseases, CHEMBL... for drugs). Use first to find IDs, then call target/disease/drug for details.

Input Schema

Name	Required	Description
`size`	No	1-50 (default 10)
`query`	Yes
`entity`	No	target \| disease \| drug (omit for all)

Output Schema

Name	Required	Description	Default
`search`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 11, 2026

removedOutput schema / properties / data

Removed value: -{
-  "properties": {
-    "search": {
-      "properties": {
-        "hits": {
-          "items": {
-            "properties": {
-              "description": {
-                "description": "Entity description",
-                "type": "string"
-              },
-              "entity": {
-                "description": "Entity type (target/disease/drug)",
-                "type": "string"
-              },
-              "id": {
-                "description": "Entity ID",
-                "type": "string"
-              },
-              "name": {
-                "description": "Entity name",
-                "type": "string"
-              }
-            },
-            "type": "object"
-          },
-          "type": "array"
-        },
-        "total": {
-          "description": "Total hits",
-          "type": "integer"
-        }
-      },
-      "type": "object"
-    }
-  },
-  "type": "object"
-}

addedOutput schema / properties / search

Added value: +{
+  "properties": {
+    "hits": {
+      "items": {
+        "properties": {
+          "description": {
+            "type": "string"
+          },
+          "entity": {
+            "type": "string"
+          },
+          "id": {
+            "type": "string"
+          },
+          "name": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "total": {
+      "type": "number"
+    }
+  },
+  "type": "object"
+}

Changed2 schema fields changedMay 24, 2026

addedInput schema / examples

Added value: +[
+  {
+    "query": "TP53"
+  },
+  {
+    "entity": "disease",
+    "query": "cancer",
+    "size": 20
+  }
+]

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "data": {
+      "properties": {
+        "search": {
+          "properties": {
+            "hits": {
+              "items": {
+                "properties": {
+                  "description": {
+                    "description": "Entity description",
+                    "type": "string"
+                  },
+                  "entity": {
+                    "description": "Entity type (target/disease/drug)",
+                    "type": "string"
+                  },
+                  "id": {
+                    "description": "Entity ID",
+                    "type": "string"
+                  },
+                  "name": {
+                    "description": "Entity name",
+                    "type": "string"
+                  }
+                },
+                "type": "object"
+              },
+              "type": "array"
+            },
+            "total": {
+              "description": "Total hits",
+              "type": "integer"
+            }
+          },
+          "type": "object"
+        }
+      },
+      "type": "object"
+    }
+  },
+  "type": "object"
+}

First observedMay 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld, non-destructive. The description adds value beyond them by specifying it returns ranked matches and the ID namespace per entity type (ENSG/EFO/CHEMBL). It does not discuss ranking factors or rate limits, but annotations carry the safety profile.

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?

Front-loads three natural-language query phrasings that help an agent match user intent, then states scope and routing. Slightly padded by the repeated quoted examples, but every clause contributes and the key guidance is early.

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?

With an output schema present and rich annotations, the description needn't explain return values. It covers purpose, entity scope, ID formats, and downstream routing, which is everything an agent needs to invoke it correctly.

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 67% with the entity enum values (target | disease | drug, omit for all) and size range already documented in the schema. The description maps entity types to ID formats but adds little syntax or behavioral meaning for the parameters themselves.

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?

States a specific verb and resource (text search across diseases, drug targets, drugs) and names the sibling tools it is not (target/disease/drug are for details). An agent can distinguish it from resolve_entity or the entity-detail tools without opening a schema.

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?

Explicitly routes usage: 'Use first to find IDs, then call target/disease/drug for details.' The when (before detail lookups) and the alternatives are named directly, leaving nothing to inference.

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

All Opentargets tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.