Lightbringer

Add review comment in Lightbringer

add_comment

Destructive

Adds a comment to the document under review, anchored to a quoted passage of the review markdown, and returns the created comment. If the quoted passage is ambiguous or cannot be located, the response indicates this along with candidate passages. A comment anchored within an existing thread is added as a reply. Targeted users with document access receive email and in-app mention notifications.

Input Schema

Name	Required	Description
`comment`	Yes	The comment text
`review_id`	Yes	The review identifier
`quoted_text`	Yes	Quoted passage from the review markdown to anchor on
`target_user_ids`	No	User identifiers to notify. Identifiers without document access are ignored.

Output Schema

Name	Required	Description	Default
`hint`	No
`hints`	No
`anchor`	No
`status`	Yes
`replyTo`	No
`commentId`	No
`candidates`	No
`instructions`	No
`mentionedUserIds`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedSep 28, 2026

changedOutput schema / properties / anchor / oneOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "block": {
-        "type": "string"
-      },
-      "kind": {
-        "const": "inline",
-        "type": "string"
-      },
-      "quotedText": {
-        "type": "string"
-      },
-      "section": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "section",
-      "block",
-      "quotedText"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "kind": {
-        "const": "section",
-        "type": "string"
-      },
-      "section": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "kind",
-      "section"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "kind": {
-        "const": "detached",
-        "type": "string"
-      },
-      "path": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ]
-      }
-    },
-    "required": [
-      "kind"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "block": {
+        "type": "string"
+      },
+      "kind": {
+        "const": "inline",
+        "type": "string"
+      },
+      "quotedText": {
+        "type": "string"
+      },
+      "section": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "section",
+      "block",
+      "quotedText"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "kind": {
+        "const": "section",
+        "type": "string"
+      },
+      "section": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "kind",
+      "section"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "kind": {
+        "const": "detached",
+        "type": "string"
+      },
+      "path": {
+        "type": [
+          "string",
+          "null"
+        ]
+      }
+    },
+    "required": [
+      "kind"
+    ],
+    "type": "object"
+  }
+]

Changed3 schema fields changedSep 8, 2026
- addedInput schema / properties / review_id / maxLength
```
Added value: +64
```
- addedInput schema / properties / review_id / minLength
```
Added value: +1
```
- addedInput schema / properties / review_id / pattern
```
Added value: +"^[A-Za-z0-9_-]+$"
```
First observedSep 1, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Beyond the annotations, it discloses real side effects: targeted users with document access get email and in-app mention notifications, and ambiguous quotes return candidate passages instead of failing blindly. That is meaningful behavioral context for a write tool. The destructiveHint=true annotation is never explained (what, if anything, can be overwritten), which is the main remaining gap.

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?

Four sentences, each carrying distinct information: purpose, failure mode, threading rule, notification side effect. It is front-loaded with the core action and free of filler. Slightly dense phrasing in the ambiguity sentence costs it the top mark.

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?

With an output schema present and full parameter coverage, the description only needs to cover intent and side effects, which it does, including the partial-success ambiguity case. It stops short of stating prerequisites (access to the review) or characterizing the destructive hint, small omissions for a mutation tool.

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%, so the baseline is 3, but the description adds genuine meaning on top: quoted_text must match review markdown and may be ambiguous, and target_user_ids triggers mention notifications while identifiers lacking document access are ignored. Only review_id receives no added semantics, which is fine given its simple pattern.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb and resource ("Adds a comment to the document under review") and states the anchoring mechanism (a quoted passage of the review markdown). It never names the closely related siblings add_discussion_comment or reply_to_comment, so an agent must infer the boundary, which keeps it out of 5 territory.

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

Usage Guidelines3/5

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

Usage context is implied rather than stated: "A comment anchored within an existing thread is added as a reply" hints at routing relative to reply_to_comment, and the ambiguity clause tells the agent what happens on failure. There is no explicit when-to-use/when-not-to-use statement, no mention of required permissions on the review, and no direct comparison with the sibling comment tools.

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

All Lightbringer 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.