Skip to main content
Glama
Sign In
Metrx MCP Server

Metrx MCP Server

by metrxbots
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Verify a Model Switch

metrx_verify_switch

Start an async verification testing whether a candidate model holds quality vs your production model on live traffic; returns a request handle immediately and charges only if a verdict is delivered.

Instructions

Start a purchased verification: would candidate_model hold quality vs prod_model on your production traffic? This action consumes one verification — $149, or $99 founding rate. No verdict, no charge. ASYNC: returns a request handle immediately and NEVER blocks — verdicts complete after days of your own traffic (armed → collecting → complete). Poll the returned handle with GET /api/verify/requests/{id}. If the balance is 0 this returns purchase guidance instead of spending. Requires an API key with the 'write' scope.

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": {
      "prod_model": "<prod_model>",
      "candidate_model": "<candidate_model>"
    },
    "name": "metrx_verify_switch"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_idNoAgent to scope the verification to
policy_idNoRouting policy to attach to
prod_modelYesCurrent production model (e.g. "gpt-5.2")
candidate_modelYesCandidate model to verify against it

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4.1/5.0
Behavior5/5

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

Annotations only say it is not read-only, not idempotent, and not destructive; the description goes much further by disclosing price ($149/$99 founding), the billing model (charge only on a verdict), the async non-blocking contract, the multi-day armed → collecting → complete lifecycle, the polling endpoint, the zero-balance behavior, and the required 'write' scope. That is exactly the behavioral context an agent cannot get from structured fields.

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?

Dense but front-loaded: the core action and the question come first, followed by cost, async contract, polling, and auth. The balance-zero sentence slightly overlaps with 'no verdict, no charge,' but each remaining clause carries distinct operational information.

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

Completeness5/5

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

There is no output schema, and the description compensates by explaining exactly what comes back (a request handle), how to use it (GET /api/verify/requests/{id}), and what states to expect. For a chargeable, asynchronous mutation with auth requirements, nothing essential is missing.

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 100%, so prod_model, candidate_model, agent_id, and policy_id are all documented in the input schema. The description reinforces the comparative relationship between the two required models but adds nothing about the optional scoping parameters (agent_id, policy_id) or any format expectations, so it sits at the baseline.

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?

The description gives a specific verb and resource ('Start a purchased verification') and frames the exact question being answered: whether candidate_model holds quality against prod_model on production traffic. It is clearly distinguishable from read-only siblings like metrx_get_verdicts, though it never names the closest sibling (metrx_buy_verification) to draw the line explicitly.

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?

It states the precondition clearly (production traffic, an existing prod model and a candidate) and discloses the cost and 'no verdict, no charge' rule, which shapes the use decision. It does not name alternative tools or say when not to use this one, which keeps it short of a 5.

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