pubmed-search-mcp

by u9401066

Overview Schema Source Related Servers Discussions Admin

Python

Remote

validate_pico_plan

Read-onlyIdempotent

Validate agent-provided P/I/C/O and question type, then return a runnable PICO search pipeline.

Instructions

Validate agent-provided P/I/C/O and return a runnable PICO pipeline.

question_type and profile are closed enums. sources is an explicit array of supported unified-search providers; malformed values fail instead of being silently replaced. When question_type is omitted, the application service infers it from the clinical question.

Input Schema

TableJSON Schema

Name	Required	Default
`c`	No
`i`	No
`o`	No
`p`	No
`limit`	No
`c_query`	No
`i_query`	No
`o_query`	No
`p_query`	No
`profile`	No	balanced
`sources`	No
`description`	No
`question_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed9 schema fields changedv0.7.7Oct 7, 2026

addedInput schema / properties / limit / anyOf

Added value: +[
+  {
+    "default": 20,
+    "maximum": 33,
+    "minimum": 1,
+    "title": "Limit",
+    "type": "integer"
+  },
+  {
+    "description": "ASCII decimal integer; the integer branch's bounds apply after conversion.",
+    "maxLength": 32,
+    "pattern": "^[ \\t\\r\\n]*-?(?:0|[1-9][0-9]*)[ \\t\\r\\n]*$",
+    "type": "string"
+  }
+]

removedInput schema / properties / limit / maximum
```
Removed value: -33
```
removedInput schema / properties / limit / minimum
```
Removed value: -1
```
removedInput schema / properties / limit / type
```
Removed value: -"integer"
```

addedInput schema / properties / profile / anyOf

Added value: +[
+  {
+    "default": "balanced",
+    "enum": [
+      "precision",
+      "balanced",
+      "recall"
+    ],
+    "title": "Profile",
+    "type": "string"
+  },
+  {
+    "pattern": "^[ \\t\\r\\n]*(?:[pP][rR][eE][cC][iI][sS][iI][oO][nN]|[bB][aA][lL][aA][nN][cC][eE][dD]|[rR][eE][cC][aA][lL][lL])[ \\t\\r\\n]*$",
+    "type": "string"
+  }
+]

removedInput schema / properties / profile / enum

Removed value: -[
-  "precision",
-  "balanced",
-  "recall"
-]

removedInput schema / properties / profile / type
```
Removed value: -"string"
```

changedInput schema / properties / question_type / anyOf

Previous value: -[
-  {
-    "enum": [
-      "therapy",
-      "diagnosis",
-      "prognosis",
-      "etiology"
-    ],
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "anyOf": [
+      {
+        "enum": [
+          "therapy",
+          "diagnosis",
+          "prognosis",
+          "etiology"
+        ],
+        "type": "string"
+      },
+      {
+        "pattern": "^[ \\t\\r\\n]*(?:[tT][hH][eE][rR][aA][pP][yY]|[dD][iI][aA][gG][nN][oO][sS][iI][sS]|[pP][rR][oO][gG][nN][oO][sS][iI][sS]|[eE][tT][iI][oO][lL][oO][gG][yY])[ \\t\\r\\n]*$",
+        "type": "string"
+      }
+    ]
+  },
+  {
+    "type": "null"
+  }
+]

changedInput schema / properties / sources / anyOf

Previous value: -[
-  {
-    "items": {
-      "enum": [
-        "pubmed",
-        "europe_pmc",
-        "openalex",
-        "semantic_scholar",
-        "core"
-      ],
-      "type": "string"
-    },
-    "maxItems": 5,
-    "minItems": 1,
-    "type": "array"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "items": {
+      "anyOf": [
+        {
+          "enum": [
+            "pubmed",
+            "europe_pmc",
+            "openalex",
+            "semantic_scholar",
+            "core"
+          ],
+          "type": "string"
+        },
+        {
+          "pattern": "^[ \\t\\r\\n]*(?:[pP][uU][bB][mM][eE][dD]|[eE][uU][rR][oO][pP][eE]_[pP][mM][cC]|[oO][pP][eE][nN][aA][lL][eE][xX]|[sS][eE][mM][aA][nN][tT][iI][cC]_[sS][cC][hH][oO][lL][aA][rR]|[cC][oO][rR][eE])[ \\t\\r\\n]*$",
+          "type": "string"
+        }
+      ]
+    },
+    "maxItems": 5,
+    "minItems": 1,
+    "type": "array"
+  },
+  {
+    "type": "null"
+  },
+  {
+    "contentMediaType": "application/json",
+    "contentSchema": {
+      "anyOf": [
+        {
+          "items": {
+            "anyOf": [
+              {
+                "enum": [
+                  "pubmed",
+                  "europe_pmc",
+                  "openalex",
+                  "semantic_scholar",
+                  "core"
+                ],
+                "type": "string"
+              },
+              {
+                "pattern": "^[ \\t\\r\\n]*(?:[pP][uU][bB][mM][eE][dD]|[eE][uU][rR][oO][pP][eE]_[pP][mM][cC]|[oO][pP][eE][nN][aA][lL][eE][xX]|[sS][eE][mM][aA][nN][tT][iI][cC]_[sS][cC][hH][oO][lL][aA][rR]|[cC][oO][rR][eE])[ \\t\\r\\n]*$",
+                "type": "string"
+              }
+            ]
+          },
+          "maxItems": 5,
+          "minItems": 1,
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Sources"
+    },
+    "description": "One JSON-encoded container; the decoded value must satisfy contentSchema.",
+    "maxLength": 1000000,
+    "type": "string"
+  },
+  {
+    "description": "One JSON code fence; after removing the fence, decode JSON and validate against x-pubmed-decodedSchema.",
+    "maxLength": 1000000,
+    "pattern": "^\\s*```(?:[jJ][sS][oO][nN])?[ \\t]*\\r?\\n[\\s\\S]*\\r?\\n```\\s*$",
+    "type": "string",
+    "x-pubmed-decodedSchema": {
+      "anyOf": [
+        {
+          "items": {
+            "anyOf": [
+              {
+                "enum": [
+                  "pubmed",
+                  "europe_pmc",
+                  "openalex",
+                  "semantic_scholar",
+                  "core"
+                ],
+                "type": "string"
+              },
+              {
+                "pattern": "^[ \\t\\r\\n]*(?:[pP][uU][bB][mM][eE][dD]|[eE][uU][rR][oO][pP][eE]_[pP][mM][cC]|[oO][pP][eE][nN][aA][lL][eE][xX]|[sS][eE][mM][aA][nN][tT][iI][cC]_[sS][cC][hH][oO][lL][aA][rR]|[cC][oO][rR][eE])[ \\t\\r\\n]*$",
+                "type": "string"
+              }
+            ]
+          },
+          "maxItems": 5,
+          "minItems": 1,
+          "type": "array"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Sources"
+    },
+    "x-pubmed-encoding": "fenced-json"
+  }
+]

Addedv0.7.2Sep 13, 2026

TDQS

A3.5/5.0

Behavior4/5

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

Annotations already establish readOnly/idempotent/non-destructive/closed-world, so the bar is lower. The description adds real traits beyond them: malformed enum/array values fail hard rather than being silently replaced, and the service infers question_type on omission. Return-pipeline shape is still undefined, keeping it short of 5.

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 the core action and output in one sentence, then adds enum/failure semantics tersely. Dense but every sentence carries information; no padding.

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

Completeness3/5

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

Covers the enum and sources semantics, but for a 13-parameter tool with no output schema the description never explains which parameters are required together, what the returned pipeline looks like, or how the *_query fields relate to the P/I/C/O fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0% across 13 parameters, so the description must carry the load. It clarifies only three fields (closed enums for question_type/profile, explicit sources array) and leaves limit, description, and the *_query fields to name inference, well short of compensating for the coverage gap.

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 ('validate agent-provided P/I/C/O') plus the output ('return a runnable PICO pipeline'). This is clearly distinguishable from siblings like unified_search or generate_search_queries.

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

Usage Guidelines2/5

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

No guidance on when to use this vs. alternatives, and no prerequisites stated. The only usage-adjacent statement is the fallback when question_type is omitted, which is behavioral rather than when-to-use advice.

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

Deploy Server

validate_pico_plan

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools