Synapse Layer — Trust Infrastructure for AI Agents

save_to_synapse

Idempotent

Persist memory with encryption at rest, sanitization, and deduplication controls.

Input Schema

Name	Required	Description
`tags`	No	Tags for categorization.
`type`	No	Event type: [MILESTONE], [DECISION], [ALERT], [AUTO-STRAT], [AUTO-OP], [AUTO-INSIGHT], [AUTO-DECISION], [AUTO-CONTEXT], [MANUAL].
`content`	Yes	The memory content to store securely.
`project`	No	Project identifier (e.g., SYNAPSE_LAYER).
`subject`	No	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.
`agent_id`	No	Agent identifier for memory isolation. Defaults to "default".
`importance`	No	Accepted for compatibility; not enforced by the API.
`project_id`	No	Project ID for authorization and memory isolation. Required for Corporate context unless the token is project-bound.
`visibility`	No	private (default) or project (visible to active members of this project).
`force_intent`	No	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.
`intent_reason`	No	Auditable reason for forcing intent classification. Max 500 characters. Ignored if force_intent is absent.

Output Schema

Name	Required	Description	Default
`status`	Yes
`memory_id`	Yes
`trust_quotient`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 29, 2026

addedInput schema / properties / project_id

Added value: +{
+  "description": "Project ID for authorization and memory isolation. Required for Corporate context unless the token is project-bound.",
+  "type": "string"
+}

addedInput schema / properties / visibility

Added value: +{
+  "description": "private (default) or project (visible to active members of this project).",
+  "enum": [
+    "private",
+    "project"
+  ],
+  "type": "string"
+}

Changed1 schema field changedSep 14, 2026

changedInput schema / properties / importance / description

Previous value: -"Importance level 1–5 (default: 3)."New value: +"Accepted for compatibility; not enforced by the API."

Changed1 schema field changedSep 2, 2026

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"
+}

Changed7 schema fields changedAug 29, 2026

removedOutput schema / properties / id

Removed value: -{
-  "type": "string"
-}

addedOutput schema / properties / memory_id
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / scope

Removed value: -{
-  "enum": [
-    "agent",
-    "tenant"
-  ],
-  "type": "string"
-}

addedOutput schema / properties / status
```
Added value: +{
+  "type": "string"
+}
```

removedOutput schema / properties / stored

Removed value: -{
-  "type": "boolean"
-}

addedOutput schema / properties / trust_quotient
```
Added value: +{
+  "type": "number"
+}
```

changedOutput schema / required

Previous value: -[
-  "id",
-  "stored",
-  "scope"
-]New value: +[
+  "memory_id",
+  "status"
+]

Changed2 schema fields changedAug 18, 2026

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"
-]

Changed2 schema fields changedAug 18, 2026

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"
+}

Changed1 schema field changedAug 17, 2026

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"
+}

Changed1 schema field changedAug 6, 2026

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

Changed1 schema field changedAug 5, 2026

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"
+}

First observedApr 13, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and openWorldHint=false; the description adds useful context that writes are encrypted at rest and sanitized, which is not in the annotations. However, 'deduplication controls' is vague — it never says what actually happens on a duplicate (skip, merge, overwrite), which is the key behavioral question for a non-destructive-but-idempotent write.

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 front-loaded sentence with zero filler, and the core action leads. It is arguably too terse for an 11-parameter tool, but nothing in it is wasted.

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 and annotations cover the safety profile, which lowers the burden. Still, for a write tool with 11 parameters involving memory isolation (subject, agent_id, project_id, visibility) and deduplication semantics, one sentence leaves significant conceptual gaps that the schema alone doesn't resolve.

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 all 11 parameters are documented in the schema and the baseline is 3. The description adds no parameter-level meaning at all, and in particular does nothing to disambiguate the confusingly overlapping 'project' vs 'project_id' pair or the isolation implications of 'subject'/'agent_id'.

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?

States a specific verb ('Persist memory') and resource, and adds the distinguishing traits (encryption at rest, sanitization, deduplication). It never distinguishes itself from the very similar siblings save_memory and store_memory, so an agent cannot tell which write tool to prefer from the description alone.

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?

There is no guidance on when to use this versus save_memory, store_memory, or list_memories, and no stated prerequisites (e.g. project_id needed for Corporate context). The reader is left to infer everything about selection from the schema.

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 tools Inspect

Try in Browser

Context All Your Agents Can ShareAgents share what they learn, hand off work, and hold it when you switch models. Start with 5 GB free.fulcradynamics.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

save_to_synapse

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources