Skip to main content
Glama

Synapse Layer — Trust Infrastructure for AI Agents

by io.github.SynapseLayer

save_memory

Idempotent

Save a memory entry to the persistent store. Alias of save_to_synapse.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoTags for categorization.
contentYesThe memory content to store securely.
subjectNoESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.
agent_idNoAgent identifier for memory isolation.
force_intentNoMANUAL OVERRIDE ONLY — use apenas quando você (humano) quer forçar explicitamente a classificação de intenção. Valores reconhecidos: preference | fact | procedural | bio | critical | operational | strategic | compliance | security | system_directive | clinical | general | ephemeral. Se não tiver certeza, NÃO preencha este campo — o sistema classifica automaticamente. Valores não reconhecidos são ignorados silenciosamente e retornados em warnings.
intent_reasonNoAuditable reason for forcing intent classification. Max 500 characters. Ignored if force_intent is absent.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYes
scopeYes
storedYes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • addedInput schema / properties / subject
      Added value: +{
+  "description": "ESCOPO1 (optional): opaque 8-128 char token ([A-Za-z0-9._:-]) that isolates memory to a single person within a shared connect-token. Omit for token-scoped behavior. Never include PII/email.",
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • changedInput schema / properties / force_intent / description
      Previous value: -"Override automatic intent classification. When set, the system skips auto-classification and uses this value directly. Accepted values: preference, fact, procedural, bio, critical, operational, strategic, compliance, security, system_directive, clinical, general, ephemeral."New value: +"MANUAL OVERRIDE ONLY — use apenas quando você (humano) quer forçar explicitamente a classificação de intenção. Valores reconhecidos: preference | fact | procedural | bio | critical | operational | strategic | compliance | security | system_directive | clinical | general | ephemeral. Se não tiver certeza, NÃO preencha este campo — o sistema classifica automaticamente. Valores não reconhecidos são ignorados silenciosamente e retornados em warnings."
    • removedInput schema / properties / force_intent / enum
      Removed value: -[
-  "preference",
-  "fact",
-  "procedural",
-  "bio",
-  "critical",
-  "operational",
-  "strategic",
-  "compliance",
-  "security",
-  "system_directive",
-  "clinical",
-  "general",
-  "ephemeral"
-]
  3. Changed2 schema fields changed
    • addedInput schema / properties / force_intent
      Added value: +{
+  "description": "Override automatic intent classification. When set, the system skips auto-classification and uses this value directly. Accepted values: preference, fact, procedural, bio, critical, operational, strategic, compliance, security, system_directive, clinical, general, ephemeral.",
+  "enum": [
+    "preference",
+    "fact",
+    "procedural",
+    "bio",
+    "critical",
+    "operational",
+    "strategic",
+    "compliance",
+    "security",
+    "system_directive",
+    "clinical",
+    "general",
+    "ephemeral"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / intent_reason
      Added value: +{
+  "description": "Auditable reason for forcing intent classification. Max 500 characters. Ignored if force_intent is absent.",
+  "maxLength": 500,
+  "type": "string"
+}
  4. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "id": {
+      "type": "string"
+    },
+    "scope": {
+      "enum": [
+        "agent",
+        "tenant"
+      ],
+      "type": "string"
+    },
+    "stored": {
+      "type": "boolean"
+    }
+  },
+  "required": [
+    "id",
+    "stored",
+    "scope"
+  ],
+  "type": "object"
+}
  5. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": true,
-  "properties": {
-    "intent": {
-      "type": "string"
-    },
-    "memory_id": {
-      "type": "string"
-    },
-    "message": {
-      "type": "string"
-    },
-    "pipeline": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "privacy_applied": {
-      "type": "boolean"
-    },
-    "quota": {
-      "additionalProperties": true,
-      "type": "object"
-    },
-    "sanitized": {
-      "type": "boolean"
-    },
-    "status": {
-      "description": "'saved' on success; 'error' with a message on rejected input.",
-      "type": "string"
-    },
-    "timestamp": {
-      "type": "string"
-    },
-    "trust_quotient": {
-      "type": "number"
-    }
-  },
-  "required": [
-    "status"
-  ],
-  "type": "object"
-}New value: +null
  6. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "intent": {
+      "type": "string"
+    },
+    "memory_id": {
+      "type": "string"
+    },
+    "message": {
+      "type": "string"
+    },
+    "pipeline": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "privacy_applied": {
+      "type": "boolean"
+    },
+    "quota": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "sanitized": {
+      "type": "boolean"
+    },
+    "status": {
+      "description": "'saved' on success; 'error' with a message on rejected input.",
+      "type": "string"
+    },
+    "timestamp": {
+      "type": "string"
+    },
+    "trust_quotient": {
+      "type": "number"
+    }
+  },
+  "required": [
+    "status"
+  ],
+  "type": "object"
+}
  7. Added
  8. Removed
  9. Added

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and idempotentHint=true, so the safety profile is covered. The description adds that the save goes to a 'persistent store', which is mildly useful, but it does not disclose other behaviors like whether existing memories are overwritten, how duplicates are handled, or any security implications.

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?

The description is two short sentences with no filler. The main action is front-loaded, and the alias note is useful for routing agents to the equivalent save_to_synapse tool.

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?

The schema and output schema are rich, so the agent has enough to call the tool. However, the description omits guidance on when this tool is preferable to the very similar sibling store_memory, and the alias note is the only contextual link to the broader toolset.

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%, so the schema already fully documents all six parameters, including the nuanced force_intent and subject fields. The description itself adds no parameter-level detail, so the baseline score of 3 is appropriate.

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 clearly states the tool's action ('Save a memory entry') and destination ('persistent store'), so an agent can tell it saves memory. It also names save_to_synapse as an alias, but it does not distinguish save_memory from the sibling store_memory, so sibling differentiation is incomplete.

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

Usage Guidelines2/5

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

The only usage-related information is 'Alias of save_to_synapse', which tells the agent these two tools are equivalent but gives no guidance on when to prefer this tool over store_memory or other memory tools. No exclusions, conditions, or alternative-selection criteria are provided.

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

All Synapse Layer — Trust Infrastructure for AI Agents toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

B3.1/5.0
Disambiguation2/5

Several tools are redundant: recall_memory is explicitly an alias of recall, and save_memory/save_to_synapse/store_memory all persist memories. This makes the tool boundary unclear for agents choosing between them, even though core operations like health_check and slo_report are distinct.

Naming Consistency2/5

Names are consistently snake_case, but verb usage is inconsistent: save_memory, save_to_synapse, and store_memory use different verbs for the same operation, and recall/recall_memory add an alias rather than following one convention. The pattern is readable but not predictable.

Tool Count3/5

Thirteen tools is not inherently excessive for an agent-memory/trust service, but the presence of multiple aliases inflates the surface and means not every tool earns its place. The effective set is smaller, making the count feel padded.

Completeness3/5

The surface covers initialization, save, list, search/recall, feedback, and handover, but there is no update or delete operation for memories. This leaves lifecycle management incomplete and may force agents to work around missing state-management operations.

Resources