Skip to main content
Glama
Sign In
Orocle Xactum

Orocle Xactum

Official
by xactum
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

xactum_verify_model

Verifies whether the model actually served matches the model you paid for using call metadata only, not prompts or outputs.

Instructions

After an LLM call: check whether the model actually served is consistent with the model claimed, using call metadata only (never prompts or outputs). Costs 0.03 USDC (x402, Base); inconclusive answers are free.

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": {
      "modelId": "<modelId>",
      "gateway": "<gateway>",
      "observedAt": "<observedAt>"
    },
    "name": "xactum_verify_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
gatewayYesProvider or gateway that served the call
modelIdYesModel you asked and paid for
latencyMsNo
observedAtYesISO-8601 time of the call
modelFieldReturnedNoThe model field in the provider's response

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

With no annotations, the description carries the full behavioral burden and does well: it states the privacy boundary (metadata only, never prompts or outputs), the exact price (0.03 USDC via x402 on Base), and that inconclusive verdicts are not billed. It stops short of describing what the response looks like or what happens if payment fails.

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?

Two sentences with no waste. Trigger and action come first, then the commercial terms and the free-inconclusive caveat, which is the right front-loading order.

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 paid verification tool with no output schema, the pricing and billing-on-inconclusive details are the critical missing pieces and both are present. The main remaining gap is that the set of possible verdicts is implied rather than stated.

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 80%, so the parameters are largely self-documenting. The description adds only the general framing that all inputs are call metadata; it gives no meaning for modelFieldReturned or latencyMs 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?

Specific verb plus resource: checks whether the model actually served matches the model claimed. It also scopes the check to call metadata and places it after an LLM call, which makes it unmistakable against the price-verification and feedback siblings.

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 phrase 'After an LLM call' clearly establishes the moment to call this tool. There are no explicit when-not conditions, but the trigger context is clear enough that an agent knows when to reach for it.

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