Skip to main content
Glama
Sign In
Metrx MCP Server

Metrx MCP Server

by metrxbots
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Get Agent Scorecard

metrx_get_scorecard
Read-onlyIdempotent

Retrieve an agent's job-contract scorecard by agent_key to review each acceptance criterion's measured value, pass/fail result, and coverage window.

Instructions

One agent's scorecard against its job contract: each acceptance criterion, the measured value, pass/fail, and the window it covers. Addressed by agent_key. Windows longer than your plan keeps are reported as insufficient, never shortened. Requires an API key with the 'read' 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": {
      "agent_key": "<agent_key>"
    },
    "name": "metrx_get_scorecard"
  }
}

Input Schema

NameRequiredDescriptionDefault
agent_keyYesThe agent_key you registered (not the row id).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A3.8/5.0
Behavior4/5

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

Goes beyond the readOnly/idempotent annotations by disclosing two real behavioral traits: windows longer than the plan retention are reported as 'insufficient, never shortened,' and an API key with 'read' scope is required. These are the kind of operational facts an agent cannot obtain from annotations. Return format is described in prose since no output schema exists.

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?

Three short sentences, front-loaded with what the tool returns, then addressing key, then edge-case behavior and auth. No filler or redundancy.

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 single-parameter read tool with no output schema, the description covers return contents, addressing, degradation behavior, and auth prerequisites. The only gap is no explicit routing versus sibling tools like metrx_get_job_contract or metrx_get_agent_detail.

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% and the schema already clarifies 'the agent_key you registered (not the row id).' The description only restates that the tool is 'addressed by agent_key,' adding no new meaning. Baseline 3 applies.

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 verb+resource: 'One agent's scorecard against its job contract,' and enumerates what it contains (acceptance criterion, measured value, pass/fail, window). This distinguishes it implicitly from metrx_get_job_contract (the contract itself) and metrx_get_agent_detail, though neither sibling is named.

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 phrase 'against its job contract' — an agent can infer this is the per-agent evaluation view rather than the contract definition. But there is no explicit when-to-use/when-not guidance or named alternative for related sibling tools.

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