Skip to main content
Glama
Sign In
Metrx MCP Server

Metrx MCP Server

by metrxbots
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Record Agent Decision

metrx_record_decision

Record a management decision for an agent (expand, re_specify, combine, retire) with a rationale, so the choice is logged as evidence on the agent page. Supply an idempotency key to prevent duplicate submissions.

Instructions

Record a management decision about an agent (expand, re_specify, combine, retire) with a rationale. The record carries the governing contract version and the scorecard at decision time as evidence, and appears on the agent page. The same decision within 60 seconds is refused as a double submit; pass idempotency_key to make a retry return the first record. Use a new key for each new decision: a key reused with a different decision is refused. 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": {
      "agent_key": "<agent_key>",
      "decision": "<decision>",
      "rationale": "<rationale>"
    },
    "name": "metrx_record_decision"
  }
}

Input Schema

NameRequiredDescriptionDefault
decisionYesexpand | re_specify | combine | retire.
agent_keyYesThe agent the decision is about.
rationaleYesWhy, in at least 20 characters; stored on the record and shown on the agent page.
idempotency_keyNoOptional. Retrying with the same key returns the first record instead of a second one.
combined_into_agent_idNoFor 'combine' only: the agent (row id) this one folds into.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.5.0

TDQS

A4.5/5.0
Behavior5/5

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

Goes well beyond the annotations: it discloses the required 'write' API scope, the 60-second duplicate refusal window, the refusal on key reuse with a different decision, the side effect that the record appears on the agent page, and the evidence captured (contract version plus scorecard at decision time). The opt-in idempotency via key is consistent with idempotentHint=false, since idempotency is not the default behavior.

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 sentences, front-loaded with purpose and then the operational rules; there is essentially no filler. Some sentences pack multiple clauses (idempotency plus key-reuse refusal), which slightly raises parsing cost but the density is justified by the content.

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 mutation tool with no output schema, the description covers side effects, evidence captured, auth scope, and failure modes, which is what an agent needs to call it correctly. It stops short of saying what the call returns (e.g., a record identifier for later reference), a minor gap given there is no output schema.

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?

Schema coverage is 100%, so baseline is 3, but the description adds real meaning for idempotency_key that the schema does not convey: retry semantics and the refusal when a key is reused with a different decision. combined_into_agent_id is left to the schema, and the rationale length floor is only in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Record a management decision about an agent') and enumerates the four decision values inline, so the agent knows exactly what this writes and to which entity. It is clearly distinguishable from read-side siblings such as metrx_get_decision_queue or metrx_get_agent_detail.

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?

Gives concrete operating guidance: the 60-second double-submit refusal, when to pass idempotency_key ('to make a retry return the first record'), and when to mint a new key. It does not name an alternative tool or state explicit when-not-to-use conditions, 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