Skip to main content
Glama
Sign In
Agent Output Guard MCP

Agent Output Guard MCP

by agenson-tools
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript

detect_hallucination_markers

Scan agent output for hallucination patterns and uncertainty markers, returning a confidence score and detailed analysis to prevent multi-agent coordination failures.

Instructions

Scan agent output for common hallucination patterns, uncertainty markers, and fabrication indicators. Critical for multi-agent reliability. Returns detailed analysis and confidence score.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "text": "<text>"
    },
    "name": "detect_hallucination_markers"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText output from another agent to analyze
content_typeNoType of content being analyzed for context-aware detectionfactual_response
source_agentNoIdentifier of the agent that generated this text
sensitivity_levelNoDetection sensitivity (high = more conservative)medium

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.4

TDQS

A3.9/5.0
Behavior3/5

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

No annotations are provided, so the description carries the safety burden. It discloses that it returns 'detailed analysis and confidence score', and mentions the tool is a scan (read-only, non-destructive). However, it doesn't disclose whether detection is deterministic or heuristic, whether sensitivity_level thresholds affect the confidence score, or how content_type context changes behavior. Moderate transparency for a read-oriented analysis tool with no annotations.

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?

Three sentences, front-loaded with the primary action, plus a purpose-driven rationale ('Critical for multi-agent reliability') and a return-value note. Each sentence earns its place; no filler or redundancy.

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?

For a parameter-rich analysis tool with no annotations and no output schema, the description reasonably covers purpose, return value, and reliability context. It could add more about output structure given there's no output schema (what does 'detailed analysis' contain?), but the 100% schema coverage compensates for parameter understanding. Slight gap on behavioral details but adequate overall.

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%, so the schema already documents all 4 parameters with descriptions. The description adds marginal value by naming key behaviors (patterns, uncertainty markers, fabrication indicators) that relate to content_type context. However, the description doesn't elaborate on how sensitivity_level or source_agent affect output beyond what the schema enum values imply. Baseline 3 is appropriate given full schema coverage.

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 has a specific verb ('scan') and resource ('agent output'), clearly states what it detects (hallucination patterns, uncertainty markers, fabrication indicators), and distinguishes it from siblings like verify_json_schema and cross_reference_check (these focus on structured validation, not semantic content analysis).

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 states it's 'critical for multi-agent reliability', implying use when validating outputs from other agents in a pipeline. However, it doesn't explicitly explain when NOT to use it versus alternatives like cross_reference_check or output_consistency_score, leaving the decision among quality tools somewhat implicit.

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