Skip to main content
Glama
Sign In
NexusWindows for Claude

NexusWindows for Claude

by pironjulien
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

logs

Read-onlyIdempotent

Review recent tool calls with arguments, attempted techniques, durations, and errors to debug Windows automation steps; inspect full daily JSONL files when needed.

Instructions

Log of the latest calls (debugging): tool, arguments, techniques tried per step, durations, errors. Full files: ~/.claude/nexus-claude/logs/YYYY-MM-DD.jsonl.

Input Schema

NameRequiredDescriptionDefault
countNo
errors_onlyNo

Output Schema

NameRequiredDescriptionDefault
pidYes
statusYes
recordsYes
versionYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv3.7.4
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$defs": {
+    "LogRecord": {
+      "properties": {
+        "args": {
+          "additionalProperties": true,
+          "title": "Args",
+          "type": "object"
+        },
+        "error": {
+          "anyOf": [
+            {
+              "type": "string"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Error"
+        },
+        "ms": {
+          "anyOf": [
+            {
+              "type": "number"
+            },
+            {
+              "type": "null"
+            }
+          ],
+          "default": null,
+          "title": "Ms"
+        },
+        "ok": {
+          "title": "Ok",
+          "type": "boolean"
+        },
+        "steps": {
+          "items": {
+            "additionalProperties": true,
+            "type": "object"
+          },
+          "title": "Steps",
+          "type": "array"
+        },
+        "tool": {
+          "title": "Tool",
+          "type": "string"
+        },
+        "ts": {
+          "title": "Ts",
+          "type": "string"
+        }
+      },
+      "required": [
+        "ts",
+        "tool",
+        "ok"
+      ],
+      "title": "LogRecord",
+      "type": "object"
+    }
+  },
+  "properties": {
+    "pid": {
+      "title": "Pid",
+      "type": "integer"
+    },
+    "records": {
+      "items": {
+        "$ref": "#/$defs/LogRecord"
+      },
+      "title": "Records",
+      "type": "array"
+    },
+    "status": {
+      "items": {
+        "type": "string"
+      },
+      "title": "Status",
+      "type": "array"
+    },
+    "version": {
+      "title": "Version",
+      "type": "string"
+    }
+  },
+  "required": [
+    "version",
+    "pid",
+    "status",
+    "records"
+  ],
+  "title": "LogsOutput",
+  "type": "object"
+}
  2. First observedv3.3.1

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, so safety is covered structurally. The description usefully discloses the returned fields and the on-disk location of the full logs, implying this is a bounded recent-window read. It does not state the actual recency/volume limits or how the count default behaves.

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?

Two tight sentences, front-loaded with what the log contains, followed by where the full files live. No filler; the location sentence earns its place by routing the agent for deeper queries. Slightly terse given the undocumented parameters, but structurally sound.

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

Completeness3/5

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

An output schema exists, so return shape needn't be explained, yet the description still helpfully lists the logged fields. The gap is on the input side—two parameters with zero coverage are left undefined, which for a low-complexity tool is the main missing piece.

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

Parameters2/5

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

Schema description coverage is 0% for both parameters, so the description must compensate and largely does not: 'count' (default 15) and 'errors_only' (default false) are never explained. The word 'errors' in the content list weakly hints at errors_only, but nothing clarifies count's meaning or bounds.

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 names a concrete resource (the log of the latest calls) and enumerates its contents—tool, arguments, techniques per step, durations, errors—which is far more specific than the bare name 'logs'. It's clearly distinguishable from the sibling action tools (act, launch, window), which mutate or drive things rather than read a log.

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 parenthetical '(debugging)' implies the use case, and the pointer to the full JSONL files tells the agent this is the recent/partial view. But there is no explicit when-to-use/when-not guidance and no naming of an alternative for full historical data beyond the file path.

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

Deploy Server

Other Tools