Skip to main content
Glama
Sign In
Metrx MCP Server

Metrx MCP Server

by metrxbots
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Get Decision Queue

metrx_get_decision_queue
Read-onlyIdempotent

Retrieves the read-only operator decision queue of approvable verdicts, blocked proposals, breaker events, and expiring evidence so API callers can review what needs attention.

Instructions

The operator decision queue, derived from real loop objects (approvable verdicts, blocked proposals, breaker events, expiring evidence). READ-ONLY: queue ACTIONS (approve/snooze/acknowledge) remain dashboard-session-only and are not exposed to API-key callers. Requires the optimization_model_v3 flag (404 while off). Response is envelope-shaped: every numeric leaf is a MeasuredValue {value, ci_low, ci_high, method, data_through}. ci fields are null unless the source payload carries a real confidence interval — never fabricated. Requires an API key with the 'read' scope.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "metrx_get_decision_queue"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4/5.0
Behavior5/5

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

Goes well past the annotations (which only declare readOnly/idempotent/non-destructive) by disclosing the feature-flag gate with its 404 failure mode, the required 'read' scope, and the non-obvious response contract that numeric leaves are MeasuredValue objects with CI fields nulled unless genuinely present. That is exactly the pre-call and post-call context an agent cannot derive 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?

Four dense sentences, all front-loaded: what it returns first, then the read-only/flag/scope constraints, then the response shape. No filler or repetition, though the flag, scope, and auth details could be condensed into a single prerequisites sentence rather than spread out.

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 no output schema, the description carries the return-value burden and does explain the envelope and MeasuredValue leaf contract, plus gating and scope requirements. It stops short of naming the top-level envelope keys (items, counts, paging), which is the one thing still missing for an agent to parse the response confidently.

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?

The tool takes zero parameters, so there is no parameter semantics to explain and the baseline of 4 applies. The description uses the freed space to describe the return shape instead, which is a reasonable substitution rather than a gap.

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 resource (the operator decision queue) and grounds it in concrete source objects: approvable verdicts, blocked proposals, breaker events, expiring evidence. An agent can tell this is a read of an aggregated decision surface rather than raw verdicts or proposals, though it never names the sibling tools it differs from (e.g. metrx_get_verdicts, metrx_get_proposals).

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?

Gives useful constraint guidance — actions (approve/snooze/acknowledge) are dashboard-session-only and unavailable to API-key callers, and the optimization_model_v3 flag must be on or the call 404s. However, it offers no explicit routing between this and the many sibling read tools that also return verdicts/proposals, leaving alternative selection to inference.

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