Skip to main content
Glama
Sign In
Hallucination Firewall

Hallucination Firewall

by Parvathy-Raj
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

rewrite_grounded

Correct a draft by replacing wrong figures with evidence values, hedging or removing unsupported claims, and adding citations to tool outputs.

Instructions

Return a corrected version of the draft: wrong figures replaced with the evidence values, unsupported claims hedged (or removed with unsupported="remove"), and citations to the tool outputs added.

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": {
      "draft": "<draft>"
    },
    "name": "rewrite_grounded"
  }
}

Input Schema

NameRequiredDescriptionDefault
draftYes
unsupportedNohedge

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full burden. It does disclose the transformation semantics well (figures replaced, claims hedged or removed, citations inserted) and 'Return a corrected version' implies a non-destructive read, but it says nothing about whether the draft is modified in place, what happens to claims with no evidence, or any limits on input size.

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?

A single sentence, front-loaded with the outcome ('Return a corrected version of the draft') followed by the three concrete edits. 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?

With an output schema present, return values need no explanation, and the description covers the behavioral contract of the rewrite plus the one non-obvious parameter. Only the draft parameter's expected content and the workflow position relative to siblings are unaddressed.

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?

Schema description coverage is 0%, so the description must compensate, and it does for the key parameter: it explains that unsupported claims are hedged by default and removed when unsupported="remove", which the schema does not convey (the schema only shows a bare string with default 'hedge'). The draft parameter is left implicit, which is a minor gap.

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 names a specific verb ('Return a corrected version') and enumerates the exact transformations applied: wrong figures replaced with evidence values, unsupported claims hedged or removed, and citations added. This is concrete enough to distinguish it from siblings like verify_claim and verify_answer, which judge rather than rewrite.

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

Usage Guidelines3/5

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

Usage is only implied: the mention of 'evidence values' and 'tool outputs' suggests it runs after evidence gathering and verification, but the description never states when to call it versus verify_answer or explain_verdict, nor any prerequisites. An agent must infer the position in the workflow.

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