Skip to main content
Glama

plot_metrics

Plots one or more metric series from a training run and returns the chart as an image, so you can visualize loss, accuracy, or reward curves from runs on remote GPUs.

Instructions

Plot one or more metric series for a run and return the chart as an image.

keys: comma-separated metric names, e.g. "loss,val_acc" or "reward".

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>",
      "keys": "<keys>"
    },
    "name": "plot_metrics"
  }
}

Input Schema

NameRequiredDescriptionDefault
keysYes
run_nameYes

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 behavioral burden. It usefully discloses the output form (a chart image), which is the key behavioral trait here, but says nothing about what happens with invalid or missing metric names, whether the run must already exist, or image format/size characteristics.

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 statement is front-loaded in one clean sentence and the key-format example is compact and useful. The dangling second block describing only `keys` is slightly awkward structurally, but no sentence 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?

This is a simple two-parameter tool and the description does cover the most important unknown, the return value being an image. It remains incomplete about failure behavior and about what metric names are valid for a given run, which an agent would still have to discover.

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 supply parameter meaning. It does explain the format of `keys` (comma-separated names, with concrete examples like "loss,val_acc"), which compensates for half the schema. `run_name` is left completely unexplained, though its meaning is largely self-evident.

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 and resource: plot metric series for a run and return a chart image. That is clearly distinguishable from a raw-read sibling like get_metrics. It does not, however, explicitly contrast itself with that sibling, so differentiation is left to inference.

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 or when-not-to-use guidance, and no mention of how this differs from get_metrics, which is the obvious alternative for metric data. The only usage signal is the implied need for a run name and metric keys.

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