Skip to main content
Glama
Sign In

Ai Model Experiments

by io.github.pipeworx-io
OverviewDiscussionsAdmin

Experiment Estimate

experiment_estimate
Read-onlyIdempotent

Dry-run cost estimate for an experiment BEFORE creating it — cell count and estimated billed cost range (at our 1.5× pricing) for prompts × models × reps. Free to call, no side effects, does not need credit balance. Same spec shape as experiment_create. Example: experiment_estimate({ prompts: ["Summarize: ..."], models: ["anthropic/claude-sonnet-4.5", "openai/gpt-5"], reps: 2 })

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "models": [
        "anthropic/claude-sonnet-4.5",
        "openai/gpt-4o-mini"
      ],
      "prompts": [
        "Summarize this article in one sentence."
      ]
    },
    "name": "experiment_estimate"
  }
}

Input Schema

NameRequiredDescriptionDefault
repsNoRepetitions per prompt×model, 1-5 (default 1)
modelsYesModel ids from experiment_models (max 12)
paramsNoOptional {system, temperature, max_tokens}
promptsYesPrompts to test (max 20)
summaryNoInclude the AI-written comparison summary stage (default true)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the safety profile is covered. The description adds meaningful operational context beyond annotations: free to call, no credit balance needed, no side effects, and that cost is calculated at 1.5x pricing.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The definition is front-loaded with the dry-run purpose and cost outputs, followed by operational caveats and a concrete example. Every sentence adds useful information for invocation, and the example clarifies the input shape despite the schema also containing examples.

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

Completeness4/5

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

With no output schema, the description provides the essential return values: cell count and estimated billed cost range. It also clarifies the free/no-credit behavior and the same-spec relation to experiment_create. Minor gaps remain around exact response fields or summary stage behavior, but the schema covers parameter details.

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 100%, so the schema already documents all five parameters including constraints like model max 12 and reps 1-5. The description only restates the high-level prompts × models × reps shape and does not add meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a precise verb and resource: a dry-run cost estimate for an experiment before creating it. It specifies the exact outputs (cell count and estimated billed cost range) and distinguishes itself from experiment_create by timing and intent.

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

Usage Guidelines4/5

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

It clearly says when to use it: BEFORE creating an experiment, and notes it shares the same spec shape as experiment_create. It does not explicitly name experiment_create as the alternative action for actually creating, but the pre-creation context is strong.

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

All Ai Model Experiments toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources