Skip to main content
Glama
zensation-ai

ZenBrain

Official
by zensation-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript

Inspect memory state

zenbrain_health
Read-only

Check how full each memory layer is: working-memory slots, interactions, episodes, facts due for review, procedures, and core blocks. Returns read-only counts only, safe anytime.

Instructions

Report how full the memory layers are: working-memory slots in use, interactions held, episodes, facts and how many are due for review, procedures, core blocks. Read-only and cheap, safe to call at any time. It returns counts only; to read the memories themselves, use zenbrain_recall.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
coreYesCore memory blocks.
workingYesWorking-memory slots in use and the slot limit.
episodicYesEpisodes stored.
semanticYesFacts stored, and how many are due for spaced-repetition review.
shortTermYesInteractions held in short-term memory.
proceduralYesProcedures stored.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.7
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "$schema": "http://json-schema.org/draft-07/schema#",
+  "additionalProperties": false,
+  "properties": {
+    "core": {
+      "additionalProperties": false,
+      "description": "Core memory blocks.",
+      "properties": {
+        "blocks": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "blocks"
+      ],
+      "type": "object"
+    },
+    "episodic": {
+      "additionalProperties": false,
+      "description": "Episodes stored.",
+      "properties": {
+        "count": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "count"
+      ],
+      "type": "object"
+    },
+    "procedural": {
+      "additionalProperties": false,
+      "description": "Procedures stored.",
+      "properties": {
+        "count": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "count"
+      ],
+      "type": "object"
+    },
+    "semantic": {
+      "additionalProperties": false,
+      "description": "Facts stored, and how many are due for spaced-repetition review.",
+      "properties": {
+        "count": {
+          "type": "number"
+        },
+        "dueForReview": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "count",
+        "dueForReview"
+      ],
+      "type": "object"
+    },
+    "shortTerm": {
+      "additionalProperties": false,
+      "description": "Interactions held in short-term memory.",
+      "properties": {
+        "interactions": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "interactions"
+      ],
+      "type": "object"
+    },
+    "working": {
+      "additionalProperties": false,
+      "description": "Working-memory slots in use and the slot limit.",
+      "properties": {
+        "max": {
+          "type": "number"
+        },
+        "used": {
+          "type": "number"
+        }
+      },
+      "required": [
+        "used",
+        "max"
+      ],
+      "type": "object"
+    }
+  },
+  "required": [
+    "working",
+    "shortTerm",
+    "episodic",
+    "semantic",
+    "procedural",
+    "core"
+  ],
+  "type": "object"
+}
  2. First observedv0.1.5

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is partly covered; the description adds cost/performance context ('cheap, safe to call at any time') and states the output shape ('counts only'). It does not add detail on latency budgets or pagination, but none is relevant for a zero-parameter count report.

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?

Three sentences: the first front-loads what is measured, the second the cost/safety profile, the third the alternative. Every sentence earns its place with no filler.

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?

An output schema exists, so return values needn't be described; the description nonetheless sets expectations ('counts only'). For a zero-parameter diagnostic tool with full annotation coverage, nothing an agent needs 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?

The tool takes no parameters, so the baseline is 4. There is nothing for the description to disambiguate, and it correctly spends no words on parameter semantics.

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?

Name and description pair a specific verb ('report how full') with the exact resources measured: working-memory slots, interactions, episodes, due-for-review facts, procedures, core blocks. It also distinguishes itself from the sibling zenbrain_recall by stating it returns counts, not contents.

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?

Explicitly frames the tool as a cheap, read-only, always-safe call and names the alternative (zenbrain_recall) for the adjacent need of reading actual memories. Both the when-to-use and the when-to-use-something-else conditions are stated.

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