Skip to main content
Glama
vassiliylakhonin

Agenda Intelligence

by vassiliylakhonin
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

agentic_interaction_trust

Triage agent-interaction trust evidence before high-stakes actions. Get a recommendation, trust signal, decision-readiness score, and missing evidence gaps for human review.

Instructions

Triage the trust evidence for an agent-mediated interaction (identity, operator or principal authorization, tool scope, session authentication, action intent) before a high-stakes action executes. Pass a structured trust_request (actor, target_surface, requested_action, dated_sources, risk_question, decision_stage) matching agentic-interaction-trust-request.schema.json. Returns a triage recommendation, trust signal, decision-readiness score, and the specific missing trust evidence. Evidence triage only: not cybersecurity monitoring, identity verification, or authorization; human review is required.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
trust_requestYesStructured agentic interaction trust request. Call get_schema('agentic_interaction_trust_request') for the full nested contract.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv1.5.0
    • changedInput schema / properties / trust_request / description
      Previous value: -"Structured agentic interaction trust request matching agentic-interaction-trust-request.schema.json."New value: +"Structured agentic interaction trust request. Call get_schema('agentic_interaction_trust_request') for the full nested contract."
    • addedInput schema / properties / trust_request / examples
      Added value: +[
+  {
+    "actor": {
+      "authentication_context": "session_cookie",
+      "declared_name": "Example Shopping Agent",
+      "declared_type": "ai_agent",
+      "declared_user_agent": "ExampleShoppingAgent/1.0",
+      "operator": "Example Consumer"
+    },
+    "asset_or_resource": "order-123",
+    "dated_sources": [
+      {
+        "date": "2026-05-28",
+        "id": "ait-1",
+        "source_type": "agent_identity_claim",
+        "title": "Declared agent identity header"
+      }
+    ],
+    "decision_stage": "pre_execution",
+    "requested_action": "complete purchase of two restricted-delivery items",
+    "requested_output": "structured_json",
+    "risk_question": "Is this agent-mediated checkout ready to allow, step up, or route to human review?",
+    "target_surface": "checkout"
+  }
+]
    • addedInput schema / properties / trust_request / properties
      Added value: +{
+  "actor": {
+    "properties": {
+      "authentication_context": {
+        "enum": [
+          "anonymous",
+          "session_cookie",
+          "api_key",
+          "oauth",
+          "mTLS",
+          "signed_agent_manifest",
+          "unknown",
+          "other"
+        ],
+        "type": "string"
+      },
+      "declared_agent_id": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "declared_name": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "declared_type": {
+        "enum": [
+          "ai_agent",
+          "automation_script",
+          "api_client",
+          "browser_bot",
+          "human_delegated_agent",
+          "unknown",
+          "other"
+        ],
+        "type": "string"
+      },
+      "declared_user_agent": {
+        "minLength": 1,
+        "type": "string"
+      },
+      "operator": {
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "declared_type",
+      "declared_name"
+    ],
+    "type": "object"
+  },
+  "asset_or_resource": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "dated_sources": {
+    "items": {
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "decision_stage": {
+    "enum": [
+      "pre_execution",
+      "in_session",
+      "post_alert",
+      "policy_review",
+      "committee_review",
+      "other"
+    ],
+    "type": "string"
+  },
+  "notes": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "requested_action": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "requested_output": {
+    "enum": [
+      "structured_json",
+      "markdown_summary",
+      "both"
+    ],
+    "type": "string"
+  },
+  "risk_question": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "target_surface": {
+    "enum": [
+      "checkout",
+      "account",
+      "api",
+      "mcp_tool",
+      "a2a_endpoint",
+      "content_or_catalog",
+      "auth_flow",
+      "support_or_messaging",
+      "other"
+    ],
+    "type": "string"
+  }
+}
    • addedInput schema / properties / trust_request / required
      Added value: +[
+  "actor",
+  "target_surface",
+  "requested_action",
+  "decision_stage",
+  "dated_sources",
+  "risk_question"
+]
  2. Addedv1.1.0

TDQS

A4.1/5.0
Behavior4/5

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

With no annotations provided, the description carries the full burden. It discloses what the tool returns (triage recommendation, trust signal, decision-readiness score, missing trust evidence), its scope ('Evidence triage only'), and a key operational constraint (human review required). It does not mention authentication requirements or side effects, but 'triage' and 'evidence triage only' imply a read-only analysis.

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?

The description is dense but purposeful: purpose, input contract, return values, scope boundaries, and human-review requirement are all covered in three sentences. It is front-loaded with the core purpose. The only minor redundancy is repeating the 'evidence triage only' boundary after already saying 'not cybersecurity monitoring, identity verification, or authorization'.

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?

Given the nested input object, no output schema, and no annotations, the description does a solid job: it specifies the required input shape, the return components, the non-goals, and the human-review requirement. The reference to an external schema file and get_schema adds a small dependency, but the description is still sufficient for an agent to decide whether to invoke this tool and what to pass.

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% because trust_request has a description, so the baseline is 3. The description adds the list of key fields (actor, target_surface, requested_action, dated_sources, risk_question, decision_stage) and references the schema file, but it does not explain the semantics of each field beyond their names. The schema's own description points to get_schema for the full nested contract, which is helpful but not fully self-contained.

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 opens with a specific verb and resource: 'Triage the trust evidence for an agent-mediated interaction' before a high-stakes action. It also names the exact input contract and output components, and explicitly distinguishes itself from cybersecurity monitoring, identity verification, and authorization, making it clearly separable from siblings like pre_action_check and validate_evidence.

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?

It clearly states when to use the tool ('before a high-stakes action executes') and what input to pass. It also provides exclusions ('not cybersecurity monitoring, identity verification, or authorization') and notes human review is required. However, it does not name specific sibling tools as alternatives, so the routing guidance is implicit rather than fully explicit.

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