Skip to main content
Glama
Sign In
Metrx MCP Server

Metrx MCP Server

by metrxbots
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

KB Prior Lookup (org-local)

metrx_kb_prior_lookup
Read-onlyIdempotent

Retrieves your organization's per-cell causal verdict counts and latest verdict summaries with confidence intervals, so you can see which task-domain combinations already have stamped evidence.

Instructions

Per-cell (task_verb × domain) summary of THIS ORG’S OWN current causal verdicts — the knowledge-base read-side, v0. TENANCY: strictly org-local; this tool never reads other orgs’ data, so zeros mean YOUR org has no stamped verdicts in that cell yet (unstamped_verdicts counts evidence predating the taxonomy). Per cell: verdict counts by evidence mode (holdout_confirmed = causal tier), observational (:value) counts, and the latest verdict summary with its savings CI. Allocation labels are deliberately absent in v0 (no cost-weight substrate exists — nothing is fabricated). 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_kb_prior_lookup"
  }
}

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?

Beyond the annotations (readOnly, idempotent, non-destructive, closed-world), the description discloses substantive behavior: strict org-local tenancy with no cross-org reads, zeros meaning absence not error, unstamped_verdicts counting pre-taxonomy evidence, the deliberate omission of allocation labels, and an API key with 'read' scope requirement. It also explains the envelope and MeasuredValue return contract, including that ci fields are null rather than fabricated — a meaningful data-trust guarantee.

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 purpose is front-loaded in the first clause before tenancy, cell contents, and response shape are layered on. It is dense and jargon-heavy, and the tenancy emphasis is slightly redundant, but with no output schema each sentence carries real information. Minor trimming would improve scanability without losing content.

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?

With no output schema and no parameters, the description carries the full burden and largely meets it: it specifies the cell keying, the metrics returned per cell (verdict counts by evidence mode, observational counts, latest verdict summary with savings CI), and the generic MeasuredValue leaf contract. An agent can call this and correctly interpret both a populated and an empty result.

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 nothing for the description to elaborate and the baseline is 4. The description correctly adds no phantom parameter guidance.

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 opening clause names a specific verb and resource: a per-cell (task_verb × domain) summary of the org's own causal verdicts, and labels itself the knowledge-base read-side. This is concrete enough that an agent knows exactly what resource it retrieves. It falls short of 5 only because it never distinguishes itself from plausible siblings such as metrx_get_verdicts, leaving the agent to infer the read-side/aggregate-vs-raw boundary.

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 resource description — call it to see what stamped verdicts exist in a cell — and the note that zeros mean 'YOUR org has no stamped verdicts in that cell yet' gives interpretation context. However, there is no explicit when-to-use, when-not-to-use, or named alternative among the many report/verdict siblings. The agent must infer the selection criteria itself.

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