Replai

Review publication candidate

publication_review

Prepares an expiring exact candidate for publication review; this does not publish.

Input Schema

Name	Required	Description	Default
`agent_id`	Yes	Agent ID from agents_list or agent_create.

Output Schema

Name	Required	Description	Default
`id`	Yes
`tests`	Yes
`pending`	Yes
`expires_at`	Yes
`draft_revision`	Yes
`source_versions`	Yes
`first_publication`	Yes
`candidate_snapshot`	Yes
`published_snapshot`	No
`publication_blockers`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 8, 2026

addedOutput schema / $defs / TestResult / properties / accepted_at

Added value: +{
+  "anyOf": [
+    {
+      "format": "date-time",
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Accepted At"
+}

Changed1 schema field changedNov 1, 2026

changedOutput schema / $defs / ConversationPolicy / description

Previous value: -"Conversation-level rules, stored as JSONB on ``bot_configs.conversation_policy``.\n\nStored legacy keys, such as the retired Agent-wide ``mode``, are ignored on read.\nWho answers first is each channel's ``reply_mode``."New value: +"Conversation-level rules, stored as JSONB on ``bot_configs.conversation_policy``.\n\nWho answers first is each channel's ``reply_mode``."

Changed1 schema field changedOct 30, 2026
- addedInput schema / properties / agent_id / description
```
Added value: +"Agent ID from agents_list or agent_create."
```

Changed6 schema fields changedOct 30, 2026

addedOutput schema / $defs / PendingChanges / properties / sources_removed / items / $ref
```
Added value: +"#/$defs/RemovedSource"
```
removedOutput schema / $defs / PendingChanges / properties / sources_removed / items / format
```
Removed value: -"uuid"
```
removedOutput schema / $defs / PendingChanges / properties / sources_removed / items / type
```
Removed value: -"string"
```

addedOutput schema / $defs / PublicationSnapshot / properties / avatar_url

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "title": "Avatar Url"
+}

addedOutput schema / $defs / PublicationSnapshot / properties / knowledge_source_names

Added value: +{
+  "additionalProperties": {
+    "type": "string"
+  },
+  "title": "Knowledge Source Names",
+  "type": "object"
+}

addedOutput schema / $defs / RemovedSource

Added value: +{
+  "description": "A source the next publication drops; name is None when no publication recorded it.",
+  "properties": {
+    "id": {
+      "format": "uuid",
+      "title": "Id",
+      "type": "string"
+    },
+    "name": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ],
+      "default": null,
+      "title": "Name"
+    }
+  },
+  "required": [
+    "id"
+  ],
+  "title": "RemovedSource",
+  "type": "object"
+}

First observedOct 28, 2026

TDQS

B3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, destructiveHint=false, and non-idempotency, so the safety profile is partially covered. The description usefully clarifies that the operation only prepares and does not publish, but leaves unexplained what state is created, why the candidate 'expires', or whether the preparation can be discarded.

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?

A single compact sentence with the non-publishing constraint front-loaded, and no filler. It is efficient, though the dense undefined term 'expiring exact candidate' costs some clarity.

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

Completeness2/5

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

There is an output schema and 100% parameter coverage, which lowers the burden, but for a non-read-only preparation step in a crowded publication_* family the description never explains what preparation entails or how it connects to publication_publish and publication_history. An agent could not confidently sequence calls from this text alone.

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 description coverage is 100% and the single agent_id parameter is documented inline as coming from agents_list or agent_create. The description adds no further meaning about the parameter, so the baseline 3 applies.

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

Purpose3/5

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

It states a verb (prepares) and a resource (publication candidate) and explicitly disclaims publishing, which separates it from publication_publish. However, the key noun phrase 'expiring exact candidate' is undefined jargon, so an agent cannot tell concretely what artifact is produced.

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?

The clause 'this does not publish' implicitly routes the agent to publication_publish for the actual publish step, which is useful. There is no explicit statement of when to call this versus publication_history, publication_restore, or publication_pause, so guidance remains inferential.

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

All Replai 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.

Resources

Need Help?