Manusights

Start a manuscript preview from its text

review_manuscript_text

Idempotent

Use this when the user wants Manusights to review, check or assess a scientific manuscript and you have its full text (for example from a file the user attached or pasted), but cannot pass the file itself. Send the complete manuscript text, not a summary or excerpt: title, abstract, every section, figure legends and references. Figures and images are not reviewed in this mode; say so to the user. Accepts up to 600,000 characters. Starts a pre-submission preview and returns a review_id right away. The preview takes a few minutes, so read it afterwards with get_manuscript_review using the same review_id. While processing, report status only; do not add a preliminary critique. Report only returned findings when ready. Each account can start a limited number of previews per day from connected apps; the result says when the limit is reached. Calling again with the same text and target journal returns the same review instead of starting another. Do not use it to write, rewrite or edit text.

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": {
      "manuscript_text": "<manuscript_text>"
    },
    "name": "review_manuscript_text"
  }
}

Input Schema

Name	Required	Description	Default
`target_journal`	No	The journal the author plans to submit to, only if the user named one.
`manuscript_text`	Yes	The full manuscript text, as written.

Output Schema

Name	Required	Description	Default
`preview`	Yes
`filename`	Yes
`next_step`	Yes
`review_id`	Yes
`created_at`	Yes
`full_review`	Yes
`target_journal`	Yes
`check_again_after_seconds`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed37 schema fields changedOct 30, 2026

removedOutput schema / properties / check_again_after_seconds / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / check_again_after_seconds / type
```
Added value: +[
+  "number",
+  "null"
+]
```

removedOutput schema / properties / created_at / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / created_at / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / filename / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / filename / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / full_review / properties / download_url / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / full_review / properties / download_url / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / full_review / properties / message / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / full_review / properties / message / type
```
Added value: +[
+  "string",
+  "null"
+]
```
removedOutput schema / properties / full_review / properties / progress_percent / anyOf
```
Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]
```
addedOutput schema / properties / full_review / properties / progress_percent / type
```
Added value: +[
+  "number",
+  "null"
+]
```

removedOutput schema / properties / full_review / properties / report_url / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / full_review / properties / report_url / type
```
Added value: +[
+  "string",
+  "null"
+]
```

changedOutput schema / properties / preview / properties / citations / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "detected": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "flagged": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      },
-      "matched": {
-        "anyOf": [
-          {
-            "type": "number"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      }
-    },
-    "required": [
-      "detected",
-      "matched",
-      "flagged"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "detected": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "flagged": {
+        "type": [
+          "number",
+          "null"
+        ]
+      },
+      "matched": {
+        "type": [
+          "number",
+          "null"
+        ]
+      }
+    },
+    "required": [
+      "detected",
+      "matched",
+      "flagged"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

removedOutput schema / properties / preview / properties / coverage_warning / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / preview / properties / coverage_warning / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / preview / properties / message / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / preview / properties / message / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / preview / properties / readiness_band / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / preview / properties / readiness_band / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / preview / properties / readiness_score / anyOf

Removed value: -[
-  {
-    "type": "number"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / preview / properties / readiness_score / type
```
Added value: +[
+  "number",
+  "null"
+]
```
removedOutput schema / properties / preview / properties / top_risks / items / properties / location / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
addedOutput schema / properties / preview / properties / top_risks / items / properties / location / type
```
Added value: +[
+  "string",
+  "null"
+]
```
removedOutput schema / properties / preview / properties / top_risks / items / properties / quote / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
addedOutput schema / properties / preview / properties / top_risks / items / properties / quote / type
```
Added value: +[
+  "string",
+  "null"
+]
```
removedOutput schema / properties / preview / properties / top_risks / items / properties / severity / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
addedOutput schema / properties / preview / properties / top_risks / items / properties / severity / type
```
Added value: +[
+  "string",
+  "null"
+]
```
removedOutput schema / properties / preview / properties / top_risks / items / properties / suggested_fix / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
addedOutput schema / properties / preview / properties / top_risks / items / properties / suggested_fix / type
```
Added value: +[
+  "string",
+  "null"
+]
```
removedOutput schema / properties / preview / properties / top_risks / items / properties / summary / anyOf
```
Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]
```
addedOutput schema / properties / preview / properties / top_risks / items / properties / summary / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / preview / properties / verdict / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / preview / properties / verdict / type
```
Added value: +[
+  "string",
+  "null"
+]
```

removedOutput schema / properties / target_journal / anyOf

Removed value: -[
-  {
-    "type": "string"
-  },
-  {
-    "type": "null"
-  }
-]

addedOutput schema / properties / target_journal / type
```
Added value: +[
+  "string",
+  "null"
+]
```

Changed3 schema fields changedOct 28, 2026

addedOutput schema / properties / preview / properties / confidence

Added value: +{
+  "anyOf": [
+    {
+      "enum": [
+        "low",
+        "medium",
+        "high"
+      ],
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

addedOutput schema / properties / preview / properties / coverage_warning

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

addedOutput schema / properties / preview / properties / top_risks / items / properties / suggested_fix

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

First observedOct 23, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Goes well beyond the annotations, which only say readOnlyHint=false, idempotentHint=true and destructiveHint=false. The description discloses the async contract (returns a review_id right away, preview takes a few minutes), the 600k character cap, per-account daily limits surfaced in the result, dedup behaviour keyed on text + target journal, and the exclusion of figures/images. It also sets a procedural guardrail (report status only, no preliminary critique; report only returned findings) that no structured field conveys.

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-loaded with the selection condition and otherwise free of filler; every clause maps to a real agent decision (completeness requirement, figures gap, async follow-up, rate limit, dedup). It is on the long side at roughly ten clauses, with the last two (dedup, no editing) slightly stacked, but no sentence is padding.

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?

For an async, open-world, rate-limited start-operation with an output schema and only two parameters, the description covers the full calling contract: input requirements, immediate return value, latency, follow-up tool, quota failure mode, and behavioural guardrails. Nothing needed to invoke or sequence it correctly is missing.

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

Parameters4/5

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

Schema coverage is 100% and the schema already states maxLength 600000 and 'full manuscript text, as written', so part of the value (the character cap) is partially redundant. The description still adds operational meaning: the text must be complete (title, abstract, every section, figure legends, references) rather than a summary, and 'same text and target journal' reveals that target_journal participates in the dedup key and thus affects the returned review.

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?

Opens with a concrete verb+resource+condition: review/check/assess a scientific manuscript when only full text (not a file) is available. This immediately distinguishes it from the sibling review_manuscript (file upload) and from get_manuscript_review (retrieval), so an agent can route correctly without opening any 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?

States the trigger ('when the user wants Manusights to review... and you have its full text'), the constraint that selects it over the alternative ('cannot pass the file itself'), an explicit exclusion ('Do not use it to write, rewrite or edit text'), and the follow-up step ('read it afterwards with get_manuscript_review using the same review_id').

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

All Manusights tools Inspect

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.