Skip to main content
Glama

rl_reward_curve

Plot a reinforcement learning run's reward curve by run name, auto-detecting reward-like metrics to visualize training progress.

Instructions

Plot the reward curve for an RL run (auto-detects reward-like metric keys).

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": "rl_reward_curve"
  }
}

Input Schema

NameRequiredDescriptionDefault
run_nameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

TDQS

B3.2/5.0
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 does disclose one meaningful trait, auto-detection of reward-like metric keys, but says nothing about what happens when no reward-like keys exist, whether the result is an image or data series, or whether the plot is persisted.

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 zero wasted words, and the auto-detection caveat is parenthetically attached to the right clause. Brevity here costs a little clarity elsewhere rather than padding, which is the right trade-off.

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 tool with no annotations and no output schema, the definition covers purpose but leaves return-value behavior unspecified (plot image? metric arrays?) and gives no failure-mode context when reward keys are absent. Adequate to attempt a call, not fully self-contained.

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?

There is one required parameter, run_name, with 0% schema description coverage, so the description must compensate. It only implies the parameter's role via "for an RL run"; the field's title (Run Name) makes the meaning largely self-evident, so the gap is small but real.

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?

The description names a specific verb and resource ("Plot the reward curve") and adds the scoping constraint "for an RL run", which separates it from general metrics tools like get_metrics or cv_training_curves. It does not explicitly name a sibling to route against, keeping it just short of a 5.

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?

Usage is implied by the phrase "for an RL run" and the reward-curve focus, so an agent can infer this is for visualizing RL training progress. There is no explicit when-to-use/when-not guidance and no named alternative such as get_metrics for raw metric values.

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