Skip to main content
Glama

groundlens_check

Read-onlyIdempotent

Check if an LLM response is hallucinated or grounded. Uses context if provided; otherwise analyzes response patterns.

Instructions

Check whether an LLM response is hallucinated or grounded.

This is the main tool. It automatically selects the right method:

  • If context is provided: uses SGI (Semantic Grounding Index) to check whether the response actually used the source material.

  • If no context: uses DGI (Directional Grounding Index) to check whether the response follows patterns typical of grounded answers.

Both methods are deterministic — same inputs always produce the same score. No second LLM is used. Scoring is based on embedding geometry.

Args: params (CheckInput): The question, response, and optional context.

Returns: str: JSON with a plain-language CHECK (Supported / Not supported by the document, or Looks grounded / Not grounded), score, level, method, message, and the raw components.

Examples: - "Check if this ChatGPT answer about our policy is accurate" → provide question + response + the policy document as context - "Is this response hallucinated?" → provide question + response (no context needed)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
paramsYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

The description adds that both methods are deterministic, no second LLM is used, and scoring is based on embedding geometry. This goes well beyond annotations (readOnlyHint, idempotentHint, destructiveHint) and provides valuable behavioral context.

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 well-structured with sections for purpose, method selection, behavior, args/returns, and examples. Every sentence adds value, and it is front-loaded with the main purpose.

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 description covers the two methods, deterministic behavior, and return format. Given the tool's complexity and presence of output schema, it is fairly complete but could include more details on the output schema or error handling.

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?

The input schema already provides descriptions for each property (question, response, context). The description adds the method selection logic based on context presence, but does not significantly enhance per-parameter meaning beyond the schema.

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 checks whether an LLM response is hallucinated or grounded. It uses specific verbs ('Check') and resource ('LLM response'), and distinguishes itself from siblings by calling itself the main tool that automatically selects the right method.

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 gives clear scenarios for when to provide context or not, and includes examples. It mentions the tool is the main one and auto-selects method, but could more explicitly advise against using the sibling tools directly.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/groundlens-dev/groundlens-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server