Skip to main content
Glama

get_metrics

Retrieves the most recent logged metric records (JSON lines) for a training run, so AI assistants can inspect run progress and training metrics by specifying a run name and tail count.

Instructions

Return the last tail logged metric records (JSON lines) for a run.

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": {
      "run_name": "<run_name>"
    },
    "name": "get_metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
tailNo
run_nameYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations, the description carries the full burden, and it does disclose the return format (JSON lines) and the tail-based selection semantics, which are genuinely useful behavioral facts. It says nothing about ordering guarantees, behavior for a missing or empty run, or size/rate limits, so the safety and failure profile remains opaque.

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?

A single front-loaded sentence with no filler, and the ordering constraint ("last") appears before the qualifier. It is arguably too terse for a 2-parameter tool with zero schema coverage, but nothing in it is wasted.

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 the description need not explain return values, and the tool itself is low complexity with only two parameters. Still, with no annotations and no parameter descriptions anywhere, gaps around run_name semantics and error behavior leave the agent without enough to call it confidently in edge cases.

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 description coverage is 0%, so the description must compensate, and it only partly does: `tail` is clarified as "the last tail logged metric records" (count of most recent records), but `run_name` is never explained beyond the phrase "for a run" — its format, source, or whether it must match an existing run is left to inference.

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 ("Return") and resource ("logged metric records") with scope ("the last tail ... for a run"), so the agent knows exactly what comes back. It does not distinguish itself from the sibling plot_metrics, which is the one alternative an agent might confuse it with.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no explicit when-to-use guidance and no mention of alternatives such as plot_metrics for visualization versus this tool for raw records. The only implicit signal is the word "logged" and the JSON-lines framing, which hints at raw retrieval rather than plotting.

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