med-lit-mcp

Overview Schema Source Related Servers Discussions Admin

resolve_duplicates

Destructive

Merge or mark duplicate literature records as distinct by recording auditable decisions for candidate pairs, keeping the chosen survivor and preventing repeated review.

Instructions

Decide pairs from list_duplicate_candidates: merge (irreversible; keep picks the survivor) or distinct (not suggested again). Rules: guide("duplicates").

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "decisions": "<decisions>"
    },
    "name": "resolve_duplicates"
  }
}

Input Schema

Name	Required	Description	Default
`project`	No	Project name from list_projects; may be omitted when only one project exists
`decisions`	Yes

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv0.3.0Oct 29, 2026

removedInput schema / $defs

Removed value: -{
-  "DuplicateDecision": {
-    "additionalProperties": false,
-    "properties": {
-      "action": {
-        "enum": [
-          "merge",
-          "distinct"
-        ],
-        "title": "Action",
-        "type": "string"
-      },
-      "candidate_id": {
-        "title": "Candidate Id",
-        "type": "integer"
-      },
-      "entity_id": {
-        "title": "Entity Id",
-        "type": "integer"
-      },
-      "keep": {
-        "default": "candidate",
-        "enum": [
-          "entity",
-          "candidate"
-        ],
-        "title": "Keep",
-        "type": "string"
-      },
-      "reason": {
-        "default": "",
-        "maxLength": 400,
-        "title": "Reason",
-        "type": "string"
-      }
-    },
-    "required": [
-      "entity_id",
-      "candidate_id",
-      "action"
-    ],
-    "title": "DuplicateDecision",
-    "type": "object"
-  }
-}

removedInput schema / properties / decisions / items / $ref
```
Removed value: -"#/$defs/DuplicateDecision"
```
addedInput schema / properties / decisions / items / additionalProperties
```
Added value: +false
```

addedInput schema / properties / decisions / items / properties

Added value: +{
+  "action": {
+    "enum": [
+      "merge",
+      "distinct"
+    ],
+    "title": "Action",
+    "type": "string"
+  },
+  "candidate_id": {
+    "title": "Candidate Id",
+    "type": "integer"
+  },
+  "entity_id": {
+    "title": "Entity Id",
+    "type": "integer"
+  },
+  "keep": {
+    "default": "candidate",
+    "enum": [
+      "entity",
+      "candidate"
+    ],
+    "title": "Keep",
+    "type": "string"
+  },
+  "reason": {
+    "default": "",
+    "maxLength": 400,
+    "title": "Reason",
+    "type": "string"
+  }
+}

addedInput schema / properties / decisions / items / required

Added value: +[
+  "entity_id",
+  "candidate_id",
+  "action"
+]

addedInput schema / properties / decisions / items / title
```
Added value: +"DuplicateDecision"
```
addedInput schema / properties / decisions / items / type
```
Added value: +"object"
```

First observedv0.1.1Sep 29, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Beyond the destructive annotation, the description discloses the critical behavior that merge is irreversible and that keep selects the survivor. It also explains that distinct prevents the pair from being suggested again, adding useful decision semantics not captured by annotations.

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 description is compact and front-loads the core decision model. Its telegraphic style is mostly effective, though the parenthetical and rule-reference fragments are slightly cryptic for an agent unfamiliar with the guide.

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?

For a destructive decision tool with an output schema, it covers the key behavioral facts: source list, merge/distinct actions, irreversibility, survivor choice, and guide reference. It omits details about the optional project selector and nested decision fields, but those are largely covered by the schema.

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 description clarifies the meaning of action values (merge vs distinct) and the keep option, but schema coverage is only 50% and it does not explain project, reason, entity_id, candidate_id, or the 50-item cap. The schema already carries the enum values and required structure, so the description adds some but not complete semantic value.

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 uses a specific verb-resource pairing: it decides duplicate pairs sourced from list_duplicate_candidates. It also names the two allowed actions, merge and distinct, which clearly distinguishes it from sibling tools like list_duplicate_candidates and merge_entities.

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 situates usage after list_duplicate_candidates and points to guide("duplicates") for rules. It does not explicitly exclude alternatives or state when to use merge_entities instead, so it stops short of full when/when-not guidance.

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