ThinkNEO Control Plane

thinkneo_log_event

Log an event within an active agent trace. Supports event types: tool_call, model_call, decision, error, pii_access, guardrail_triggered. Returns event_id and running session cost. Requires authentication.

Input Schema

TableJSON Schema

Name	Required	Description
`cost`	No	Estimated cost in USD for this event (e.g., 0.003 for an API call)
`metadata`	No	Optional dict with additional event context
`tool_name`	No	Name of the tool called (for tool_call events)
`event_type`	Yes	Event type: 'tool_call', 'model_call', 'decision', 'error', 'pii_access', or 'guardrail_triggered'
`latency_ms`	No	Latency in milliseconds for this event
`model_name`	No	Model used (for model_call events, e.g., 'gpt-4o', 'claude-sonnet-4-20250514')
`session_id`	Yes	Session ID from thinkneo_start_trace
`input_summary`	No	Brief summary of the input (max 500 chars, truncated if longer)
`output_summary`	No	Brief summary of the output (max 500 chars, truncated if longer)

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed13 schema fields changedJun 26, 2026

addedInput schema / properties / cost

Added value: +{
+  "default": 0,
+  "description": "Estimated cost in USD for this event (e.g., 0.003 for an API call)",
+  "title": "Cost",
+  "type": "number"
+}

removedInput schema / properties / event_type / default
```
Removed value: -"info"
```

changedInput schema / properties / event_type / description

Previous value: -"Event type (info, warning, error, metric)"New value: +"Event type: 'tool_call', 'model_call', 'decision', 'error', 'pii_access', or 'guardrail_triggered'"

addedInput schema / properties / input_summary

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Brief summary of the input (max 500 chars, truncated if longer)",
+  "title": "Input Summary"
+}

addedInput schema / properties / latency_ms

Added value: +{
+  "default": 0,
+  "description": "Latency in milliseconds for this event",
+  "title": "Latency Ms",
+  "type": "integer"
+}

removedInput schema / properties / message

Removed value: -{
-  "default": "",
-  "description": "Event message",
-  "title": "Message",
-  "type": "string"
-}

addedInput schema / properties / metadata

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Optional dict with additional event context",
+  "title": "Metadata"
+}

addedInput schema / properties / model_name

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Model used (for model_call events, e.g., 'gpt-4o', 'claude-sonnet-4-20250514')",
+  "title": "Model Name"
+}

addedInput schema / properties / output_summary

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Brief summary of the output (max 500 chars, truncated if longer)",
+  "title": "Output Summary"
+}

addedInput schema / properties / session_id

Added value: +{
+  "description": "Session ID from thinkneo_start_trace",
+  "title": "Session Id",
+  "type": "string"
+}

addedInput schema / properties / tool_name

Added value: +{
+  "anyOf": [
+    {
+      "type": "string"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Name of the tool called (for tool_call events)",
+  "title": "Tool Name"
+}

removedInput schema / properties / trace_id

Removed value: -{
-  "description": "Trace ID to attach this event to",
-  "title": "Trace Id",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "trace_id"
-]New value: +[
+  "session_id",
+  "event_type"
+]

Changed13 schema fields changedMay 11, 2026

removedInput schema / properties / cost

Removed value: -{
-  "default": 0,
-  "description": "Estimated cost in USD for this event (e.g., 0.003 for an API call)",
-  "title": "Cost",
-  "type": "number"
-}

addedInput schema / properties / event_type / default
```
Added value: +"info"
```

changedInput schema / properties / event_type / description

Previous value: -"Event type: 'tool_call', 'model_call', 'decision', 'error', 'pii_access', or 'guardrail_triggered'"New value: +"Event type (info, warning, error, metric)"

removedInput schema / properties / input_summary

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Brief summary of the input (max 500 chars, truncated if longer)",
-  "title": "Input Summary"
-}

removedInput schema / properties / latency_ms

Removed value: -{
-  "default": 0,
-  "description": "Latency in milliseconds for this event",
-  "title": "Latency Ms",
-  "type": "integer"
-}

addedInput schema / properties / message

Added value: +{
+  "default": "",
+  "description": "Event message",
+  "title": "Message",
+  "type": "string"
+}

removedInput schema / properties / metadata

Removed value: -{
-  "anyOf": [
-    {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Optional dict with additional event context",
-  "title": "Metadata"
-}

removedInput schema / properties / model_name

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Model used (for model_call events, e.g., 'gpt-4o', 'claude-sonnet-4-20250514')",
-  "title": "Model Name"
-}

removedInput schema / properties / output_summary

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Brief summary of the output (max 500 chars, truncated if longer)",
-  "title": "Output Summary"
-}

removedInput schema / properties / session_id

Removed value: -{
-  "description": "Session ID from thinkneo_start_trace",
-  "title": "Session Id",
-  "type": "string"
-}

removedInput schema / properties / tool_name

Removed value: -{
-  "anyOf": [
-    {
-      "type": "string"
-    },
-    {
-      "type": "null"
-    }
-  ],
-  "default": null,
-  "description": "Name of the tool called (for tool_call events)",
-  "title": "Tool Name"
-}

addedInput schema / properties / trace_id

Added value: +{
+  "description": "Trace ID to attach this event to",
+  "title": "Trace Id",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "session_id",
-  "event_type"
-]New value: +[
+  "trace_id"
+]

AddedApr 18, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=false), the description discloses that authentication is required and that the call returns event_id and running session cost, implying session state is affected. This is useful context, though it doesn't detail side effects like whether it appends to an immutable log.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences, front-loaded with purpose, each sentence adds new information (scope, event types, return value, auth). No wasted words.

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?

The description covers purpose, scope, event types, return value, and authentication. It doesn't mention that session_id originates from thinkneo_start_trace, but the schema already specifies that; the output schema exists, so return details needn't be expanded. Adequately complete for a logging tool.

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 coverage is 100%—every parameter has a description in the schema. The tool description adds no parametric meaning beyond repeating the event_type list, so baseline 3 applies.

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 opens with a specific verb+resource ('Log an event within an active agent trace') and enumerates six supported event types, making its scope unmistakable. It also states return values, distinguishing it from sibling logging tools like thinkneo_log_decision and thinkneo_a2a_log.

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?

The description explicitly frames usage as within an active trace and lists the event types it supports, providing clear context. However, it does not mention alternatives or exclusions, e.g., when to use thinkneo_log_decision instead, so it falls short of a 5.

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

All ThinkNEO Control Plane 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.