GENESIS ProofRelay MCP Verifier

Summarize agent action log

proofrelay.summarize_agent_action_log

Read-onlyIdempotent

Summarize public-safe agent action log counts and hashes into a governance review profile without ingesting raw logs or traces.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`action_log`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed6 schema fields changedAug 21, 2026

removedInput schema / $defs

Removed value: -{
-  "AgentActionLogSummaryInput": {
-    "description": "Hash-only agent action log summary input.",
-    "properties": {
-      "action_count": {
-        "description": "Number of actions summarized.",
-        "minimum": 0,
-        "title": "Action Count",
-        "type": "integer"
-      },
-      "action_type_counts": {
-        "additionalProperties": {
-          "type": "integer"
-        },
-        "description": "Public action type counts.",
-        "title": "Action Type Counts",
-        "type": "object"
-      },
-      "actor_hash": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Optional actor hash.",
-        "title": "Actor Hash"
-      },
-      "authority_hash": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Optional authority hash.",
-        "title": "Authority Hash"
-      },
-      "error_count": {
-        "default": 0,
-        "description": "Number of failed actions.",
-        "minimum": 0,
-        "title": "Error Count",
-        "type": "integer"
-      },
-      "first_ts_ms": {
-        "anyOf": [
-          {
-            "type": "integer"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "First action timestamp.",
-        "title": "First Ts Ms"
-      },
-      "last_ts_ms": {
-        "anyOf": [
-          {
-            "type": "integer"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Last action timestamp.",
-        "title": "Last Ts Ms"
-      },
-      "log_hash": {
-        "description": "SHA-256 hash of the action log.",
-        "title": "Log Hash",
-        "type": "string"
-      },
-      "payment_context_hash": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Optional payment context hash.",
-        "title": "Payment Context Hash"
-      },
-      "session_hash": {
-        "anyOf": [
-          {
-            "type": "string"
-          },
-          {
-            "type": "null"
-          }
-        ],
-        "default": null,
-        "description": "Optional session hash.",
-        "title": "Session Hash"
-      }
-    },
-    "required": [
-      "log_hash",
-      "action_count"
-    ],
-    "title": "AgentActionLogSummaryInput",
-    "type": "object"
-  }
-}

removedInput schema / properties / action_log / $ref

Removed value: -"#/$defs/AgentActionLogSummaryInput"

addedInput schema / properties / action_log / properties

Added value: +{
+  "action_count": {
+    "minimum": 0,
+    "type": "integer"
+  },
+  "action_type_counts": {
+    "additionalProperties": {
+      "type": "integer"
+    },
+    "type": "object"
+  },
+  "actor_hash": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "authority_hash": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "error_count": {
+    "minimum": 0,
+    "type": "integer"
+  },
+  "first_ts_ms": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "last_ts_ms": {
+    "anyOf": [
+      {
+        "type": "integer"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "log_hash": {
+    "type": "string"
+  },
+  "payment_context_hash": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  },
+  "session_hash": {
+    "anyOf": [
+      {
+        "type": "string"
+      },
+      {
+        "type": "null"
+      }
+    ]
+  }
+}

addedInput schema / properties / action_log / required

Added value: +[
+  "log_hash",
+  "action_count"
+]

addedInput schema / properties / action_log / type
```
Added value: +"object"
```

removedInput schema / title

Removed value: -"summarize_agent_action_logArguments"

First observedJun 23, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the barrier is low. The description adds valuable transparency by emphasizing it does not ingest raw logs or traces, which reassures the agent about privacy and scope. It does not contradict annotations, and the addition of 'public-safe' clarifies the security posture.

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 a single, well-formed sentence that is front-loaded with the primary action and includes a crucial negative ('without ingesting raw logs or traces'). No wasted words; every clause adds meaning.

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

Completeness4/5

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

The tool is relatively simple with one parameter and an output schema, and annotations cover safety aspects. The description is sufficient for basic usage, but given the nested object schema and the governance context, a bit more detail on expected inputs or output format would be helpful. Yet the output schema may compensate.

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?

With schema description coverage at 0%, the description must compensate, and it partially does by conveying the 'action_log' parameter contains counts and hashes. However, it does not elaborate on individual nested fields like 'log_hash' or 'action_type_counts', relying on the schema for structure. This is acceptable given the single parameter and clear high-level intent.

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?

The description clearly states the tool's purpose: summarizing 'public-safe agent action log counts and hashes' into a 'governance review profile' while explicitly noting it does not ingest raw logs or traces. This distinguishes it from sibling tools that build evidence or proofs, and uses specific verbs and resources.

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

Usage Guidelines4/5

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

The description implies usage for governance review without needing to process raw logs, which provides clear context. However, it does not explicitly state when not to use this tool or mention alternatives, though the sibling list suggests related but distinct tools like 'build_audit_pack_manifest' or 'build_closing_proof_pack'.

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

All GENESIS ProofRelay MCP Verifier tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?