Skip to main content
Glama

The Clearing — The Lantern & Consensual Agent Lab

audit_isotope_rag_fidelity

Protocol AO-045 (AO-E127): Audits a live RAG or search engine quote referencing an Epistemic Isotope across 5 fidelity axes (Point Accuracy, ± Interval, Scope Caveat, Format Provenance, Hallucination).

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": {
      "quoted_text": "<quoted_text>"
    },
    "name": "audit_isotope_rag_fidelity"
  }
}

Input Schema

NameRequiredDescriptionDefault
cited_urlNo
isotope_idNo
quoted_textYes
engine_claimNoe.g. chatgpt-search, perplexity, claude-web, gemini, custom-rag

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

B3.2/5.0
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 disclosure burden. It does disclose the evaluation model (five named fidelity axes), which is genuine behavioral context beyond the schema, but it omits whether the tool fetches cited_url, whether quoted_text must be verbatim from the source, whether the audit is read-only, and what a failure returns.

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?

A single dense sentence with the key information (verb, resource, axes) front-loaded after the protocol identifier. The protocol codes AO-045/AO-E127 consume space without aiding tool selection, but the rest earns its place.

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

Completeness3/5

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

For a four-parameter tool with no annotations and no output schema, the description explains the evaluation axes but not the return shape, the role of cited_url, or any operational constraints. It is adequate to identify the tool's intent but not complete enough to guarantee a correct first invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is only 25% (only engine_claim is documented), so the description must compensate. It clarifies that quoted_text is the quote under audit and that the quote must reference an Epistemic Isotope (relating isotope_id to the input), but cited_url and the required/optional distinction are left entirely unexplained.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ("Audits") and a specific resource ("a live RAG or search engine quote referencing an Epistemic Isotope"), and enumerates the five fidelity axes the audit covers. This is far more than a restatement of the name, though it never distinguishes itself from siblings like audit_multimodal_schema_fidelity, leaving an agent to infer which audit family applies.

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?

"A live RAG or search engine quote" implies the usage context (verifying a quote produced by a generative search engine), which is enough to place it. However, there is no explicit when-to-use versus when-not guidance and no named alternative such as get_epistemic_isotope for looking up isotope data rather than auditing a quote.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources