Synapse Layer — Trust Infrastructure for AI Agents

search

Read-only

Search persisted memory across agent scopes using full-text matching. Governance: requires reason (10–200 chars) because results contain plaintext content.

Input Schema

Name	Required	Description
`limit`	No	Maximum results to return (1–50, default: 20).
`query`	Yes	Search query — natural language or keywords.
`scope`	No	Explicit search scope. "agent" (default, fail-closed) = limits search to the given agent_id (or the token agent). "tenant" = cross-agent search within the authenticated tenant. If omitted with agent_id present, "agent" is inferred; if both omitted, the token agent is used (verified-token scope).
`reason`	Yes	REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Human-readable justification for retrieving PLAINTEXT memory. Without this parameter the call WILL fail with code -32602. Example: "Checking prior migration decisions for the user."
`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 (canonical or alias). Used only when scope="agent" or scope is inferred.
`project_id`	No	Project ID for authorization and memory isolation. Required for Corporate context unless the token is project-bound.

Output Schema

Name	Required	Description	Default
`count`	Yes
`scope`	Yes
`results`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field 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"
+}

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"
+}

Changed1 schema field changedAug 17, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "type": "number"
+    },
+    "results": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "scope": {
+      "enum": [
+        "agent",
+        "tenant"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "results",
+    "count",
+    "scope"
+  ],
+  "type": "object"
+}

Changed2 schema fields changedAug 14, 2026

addedInput schema / properties / reason

Added value: +{
+  "description": "REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Human-readable justification for retrieving PLAINTEXT memory. Without this parameter the call WILL fail with code -32602. Example: \"Checking prior migration decisions for the user.\"",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "query"
-]New value: +[
+  "query",
+  "reason"
+]

Changed2 schema fields changedAug 6, 2026

removedInput schema / properties / reason

Removed value: -{
-  "description": "REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Human-readable justification for retrieving PLAINTEXT memory. Without this parameter the call WILL fail with code -32602. Example: \"Checking prior migration decisions for the user.\"",
-  "type": "string"
-}

changedInput schema / required

Previous value: -[
-  "query",
-  "reason"
-]New value: +[
+  "query"
+]

Changed3 schema fields changedAug 6, 2026

addedInput schema / properties / reason

Added value: +{
+  "description": "REQUIRED (10–200 chars). Audit policy: MEMORY_EXPORT_GOVERNANCE_V1. Human-readable justification for retrieving PLAINTEXT memory. Without this parameter the call WILL fail with code -32602. Example: \"Checking prior migration decisions for the user.\"",
+  "type": "string"
+}

changedInput schema / required

Previous value: -[
-  "query"
-]New value: +[
+  "query",
+  "reason"
+]

changedOutput schema / (root)

Previous value: -{
-  "additionalProperties": true,
-  "properties": {
-    "agent_id": {
-      "type": "string"
-    },
-    "count": {
-      "type": "number"
-    },
-    "query": {
-      "type": "string"
-    },
-    "results": {
-      "items": {
-        "additionalProperties": true,
-        "properties": {
-          "agent": {
-            "type": "string"
-          },
-          "content": {
-            "type": "string"
-          },
-          "intent": {
-            "type": "string"
-          },
-          "is_critical": {
-            "type": "boolean"
-          },
-          "memory_type": {
-            "type": "string"
-          },
-          "timestamp": {
-            "type": "string"
-          },
-          "trust_quotient": {
-            "type": "number"
-          }
-        },
-        "type": "object"
-      },
-      "type": "array"
-    },
-    "scope": {
-      "type": "string"
-    },
-    "scope_source": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "results",
-    "count"
-  ],
-  "type": "object"
-}New value: +null

Changed1 schema field changedAug 5, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "additionalProperties": true,
+  "properties": {
+    "agent_id": {
+      "type": "string"
+    },
+    "count": {
+      "type": "number"
+    },
+    "query": {
+      "type": "string"
+    },
+    "results": {
+      "items": {
+        "additionalProperties": true,
+        "properties": {
+          "agent": {
+            "type": "string"
+          },
+          "content": {
+            "type": "string"
+          },
+          "intent": {
+            "type": "string"
+          },
+          "is_critical": {
+            "type": "boolean"
+          },
+          "memory_type": {
+            "type": "string"
+          },
+          "timestamp": {
+            "type": "string"
+          },
+          "trust_quotient": {
+            "type": "number"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "scope": {
+      "type": "string"
+    },
+    "scope_source": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "results",
+    "count"
+  ],
+  "type": "object"
+}

Changed1 schema field changedApr 29, 2026

changedInput schema / properties / scope / description

Previous value: -"Explicit search scope. \"agent\" (default, fail-closed) = limits search to the given agent_id (or the token agent). \"tenant\" = cross-agent search within the authenticated tenant. If omitted with agent_id present, \"agent\" is inferred; if both omitted, the token agent is used with a warning."New value: +"Explicit search scope. \"agent\" (default, fail-closed) = limits search to the given agent_id (or the token agent). \"tenant\" = cross-agent search within the authenticated tenant. If omitted with agent_id present, \"agent\" is inferred; if both omitted, the token agent is used (verified-token scope)."

Changed2 schema fields changedApr 28, 2026

changedInput schema / properties / agent_id / description

Previous value: -"Optional: restrict search to a specific agent."New value: +"Agent identifier (canonical or alias). Used only when scope=\"agent\" or scope is inferred."

addedInput schema / properties / scope

Added value: +{
+  "description": "Explicit search scope. \"agent\" (default, fail-closed) = limits search to the given agent_id (or the token agent). \"tenant\" = cross-agent search within the authenticated tenant. If omitted with agent_id present, \"agent\" is inferred; if both omitted, the token agent is used with a warning.",
+  "enum": [
+    "agent",
+    "tenant"
+  ],
+  "type": "string"
+}

Changed2 schema fields changedApr 27, 2026

changedInput schema / properties / agent_id / description

Previous value: -"Agent identifier (canonical or alias). Used only when scope=\"agent\" or scope is inferred."New value: +"Optional: restrict search to a specific agent."

removedInput schema / properties / scope

Removed value: -{
-  "description": "Explicit search scope. \"agent\" (default, fail-closed) = limits search to the given agent_id (or the token agent). \"tenant\" = cross-agent search within the authenticated tenant. If omitted with agent_id present, \"agent\" is inferred; if both omitted, the token agent is used with a warning.",
-  "enum": [
-    "agent",
-    "tenant"
-  ],
-  "type": "string"
-}

Changed2 schema fields changedApr 23, 2026

changedInput schema / properties / agent_id / description

Previous value: -"Optional: restrict search to a specific agent."New value: +"Agent identifier (canonical or alias). Used only when scope=\"agent\" or scope is inferred."

addedInput schema / properties / scope

Added value: +{
+  "description": "Explicit search scope. \"agent\" (default, fail-closed) = limits search to the given agent_id (or the token agent). \"tenant\" = cross-agent search within the authenticated tenant. If omitted with agent_id present, \"agent\" is inferred; if both omitted, the token agent is used with a warning.",
+  "enum": [
+    "agent",
+    "tenant"
+  ],
+  "type": "string"
+}

First observedApr 13, 2026

TDQS

B3.3/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds the governance consequence — a reason of 10–200 chars is mandatory and results carry plaintext content — but that is largely a restatement of the reason parameter's schema text rather than new behavioral disclosure (no pagination, ranking, or failure modes described).

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 and followed by the single governance constraint. Nothing is padded and the critical compliance rule is placed where it will be read.

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?

With an output schema present, return values need no explanation, but for a 7-parameter search inside a cluster of near-synonymous retrieval tools the description should still explain how it differs from recall/recall_memory/list_memories. That disambiguation is missing.

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% and the schema already documents scope semantics, limit range, subject token, and the reason constraint in detail. The description repeats the reason length constraint without adding meaning beyond the schema, so the baseline 3 applies.

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 and resource (search persisted memory) plus the retrieval mode (full-text matching) and scope dimension (agent scopes). It is clearer than a bare 'search' but never names which sibling (recall, recall_memory, list_memories) it replaces, so an agent still has to infer the boundary.

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 instruction is a governance rule about the reason parameter — there is no statement of when to call this versus list_memories, recall, or recall_memory, nor any exclusion. With four similarly named retrieval siblings, the missing routing guidance is a real gap.

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.

search

Input Schema

Output Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources