Skip to main content
Glama
Reliquary MCP

Reliquary MCP

Official
by reliquadotai

reliquary_run_monitor

Read-onlyIdempotent

Read a stored public training run snapshot with source clocks, checkpoints, benchmark evidence, token composition and GPU observations, preserving missing or stale states without granting trainer control.

Instructions

Read one stored public training run snapshot, including source clocks, checkpoints, benchmark evidence, actual response-token composition and declared GPU observations. Preserve missing/stale states. This grants no trainer or operator control.

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": "reliquary_run_monitor"
  }
}

Input Schema

NameRequiredDescriptionDefault
runNo

Output Schema

NameRequiredDescriptionDefault
dataYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.12.1

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, yet the description adds real behavior: missing and stale states are surfaced rather than filled in, GPU figures are 'declared' (self-reported, not verified), and the call confers no trainer or operator control. That is useful epistemic framing beyond the annotations, though nothing is said about what an unknown run identifier yields.

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?

Three short sentences, front-loaded with the read action, followed by contents and then the scope caveat. The contents list is somewhat redundant given a separate output schema exists, but it is compact and each clause carries information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explaining, and the safety profile is covered by annotations. The remaining gap is behavioral in the input dimension: with a single optional `run` parameter at 0% schema description coverage, the definition never says what an identifier looks like or what happens when it is omitted.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Placeholder.

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?

Specific verb+resource: 'Read one stored public training run snapshot', and it enumerates what the snapshot contains (clocks, checkpoints, benchmark evidence, token composition, GPU observations). The singular 'one ... run' reading contrasts implicitly with the catalog-style siblings, though no 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?

The phrase 'one stored public training run snapshot' implies single-run retrieval versus a listing tool, but there is no explicit when-to-use/when-not or named alternative. The scope-boundary sentence ('grants no trainer or operator control') tells the agent what it cannot do, which is context rather than routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.