Skip to main content
Glama
Sign In
Metrx MCP Server

Metrx MCP Server

by metrxbots
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Get Causal Verdicts

metrx_get_verdicts
Read-onlyIdempotent

Get org-scoped current causal verdict summaries by agent, production/candidate model, and task category, including evidence mode, pair counts, non-inferiority, savings CI, judge model, and expiry.

Instructions

Org-scoped CURRENT causal-verdict summaries: per (agent, prod_model, candidate_model, task_category) — verdict, evidence mode/regime, pair counts, non-inferiority, savings CI, judge model, expiry. Observational (:value) rows are flagged. Summaries only: no gate flags, no evidence-pack contents (those stay dashboard-session-only). Read-only. 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_verdicts"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

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 already cover read-only/idempotent/non-destructive, and the description adds substantive behavior beyond them: org scoping, current-only vs historical, observational rows flagged, summaries deliberately omit gate flags and evidence packs, the envelope/MeasuredValue return shape, the guarantee that CI fields are null rather than fabricated, and the required 'read' scope API key. No claim conflicts with the annotations.

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?

The content is dense but front-loaded: identity and scoping first, exclusions second, return shape third, auth last. It is somewhat sentence-heavy with stacked clauses, and a few items (e.g., savings CI, judge model) are listed without explaining their relevance, but nothing is clearly padding.

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, so the description carries the return-value burden itself and does so: it names the envelope shape and the MeasuredValue leaf structure including null-CI semantics. Combined with scope, exclusions, and auth requirements, an agent has what it needs to call and interpret this correctly.

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; the baseline of 4 applies. The description does not waste space inventing parameters and instead clarifies the implicit scoping (org-level, current).

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 concrete verb and resource ('Org-scoped CURRENT causal-verdict summaries') and specifies the exact key tuple (agent, prod_model, candidate_model, task_category), which is far more specific than the title alone. It also draws a boundary against dashboard-session data ('no gate flags, no evidence-pack contents'), but never names a sibling tool it should be preferred over.

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?

Usage is implied by the content ('current verdict summaries', 'observational rows flagged') and by the exclusion of evidence-pack detail, but there is no explicit when-to-use/when-not guidance and no reference to competing siblings such as actuations or experiment results. An agent can infer the situation, but must guess at routing trade-offs.

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