Skip to main content
Glama

cv_training_curves

Plots loss, accuracy, mAP, and IoU curves for a computer-vision run, auto-detecting available metrics so you can inspect training progress.

Instructions

Plot standard CV metrics for a run (loss / accuracy / mAP / IoU — auto-detected).

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": "cv_training_curves"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_nameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

C2.9/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden. It discloses that metric types are auto-detected, but says nothing about whether the plot is rendered inline, saved to a file, or returned as an image, nor what happens if the run name is unknown or the run lacks metrics. For an unannotated tool this is thin.

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; the parenthetical metric list is genuinely informative rather than decorative. It could be slightly improved by adding one clause on output format, but nothing 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?

For a one-parameter visualization tool, the description covers what is plotted but not how the result is delivered or what preconditions the run must satisfy. With no annotations and no output schema to fall back on, a bit more behavioral context would be needed for full completeness.

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?

Only one parameter (run_name) exists and schema description coverage is 0%, so the schema adds nothing. The description implies run_name identifies an existing run to plot, but gives no naming format, case sensitivity, or how to discover valid run names.

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 standard CV metrics for a run", and enumerates the metrics (loss / accuracy / mAP / IoU). This distinguishes it from data-returning siblings like get_metrics or get_logs, though it never names an alternative explicitly.

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 guidance, and no mention of alternatives such as get_metrics for raw numbers versus this tool for a visual. The intended use (visualizing a run's training progress) is only implied by the word "Plot".

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