Skip to main content
Glama
FractalAI MCP Server

FractalAI MCP Server

by johnInarti

Verify a post-quantum signature

verify_proof

Check a post-quantum ML-DSA-65/Dilithium-3 signature against its public key to confirm the exact signed bytes and return a valid verdict.

Instructions

Verify a post-quantum (ML-DSA-65 / Dilithium-3, NIST FIPS 204) signature against its public key. Free, no payment. Returns { valid, verdict }. A valid result proves the exact bytes in signed_message_b64 were signed by the given key; it says nothing about their truthfulness. For a signature from pqc_sign over a hex digest D, signed_message_b64 = base64(utf8(D)).

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": {
      "signed_message_b64": "<signed_message_b64>",
      "signature": "<signature>",
      "public_key": "<public_key>"
    },
    "name": "verify_proof"
  }
}

Input Schema

NameRequiredDescriptionDefault
signatureYesBase64 ML-DSA-65 / Dilithium-3 signature to check.
public_keyYesBase64 ML-DSA-65 / Dilithium-3 public key.
signed_message_b64YesBase64 of the exact bytes that were signed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A4.4/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and mostly does: it discloses the return shape { valid, verdict }, the cost (free), and an important scoping caveat that a valid result proves only byte-level signing, not truthfulness of content. It leaves 'verdict' values undefined and says nothing about error-vs-false behavior or determinism.

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?

Four short sentences, purpose and algorithm front-loaded, then cost, then return shape, then the critical interpretation caveat and the encoding recipe. No sentence is filler and nothing is buried.

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 3-parameter read-only verifier with no output schema, the description covers cost, return fields, and interpretation limits well. The one gap is that 'verdict' is never explained, which matters because no output schema exists to resolve it.

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 coverage is 100%, so baseline is 3, but the description goes beyond it by explaining the exact byte semantics of signed_message_b64 and how it derives from a pqc_sign digest, which the schema field text ('Base64 of the exact bytes that were signed') does not spell out. Signature and public_key get no extra treatment 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?

Names a specific verb (verify) and resource (post-quantum signature), and pins the algorithm family precisely (ML-DSA-65 / Dilithium-3, NIST FIPS 204), which lets an agent distinguish it from the sibling pqc_sign without opening the schema.

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?

States cost context ('Free, no payment') and gives a concrete cross-tool recipe: for output from pqc_sign over a hex digest D, signed_message_b64 = base64(utf8(D)). That is real when-and-how guidance tied to a named sibling, but there are no explicit when-not conditions or named alternatives for other verification paths.

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