Skip to main content
Glama
thejaredchapman

EvalForge Lite

by thejaredchapman
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Hybrid

run_comparison

Runs test prompts against up to four models, scores each response with LLM judges and rule checks, then returns grades, cost, latency, and a verdict.

Instructions

Run a set of test-case prompts against a set of models, scoring each response.

Each test case may include an optional "rubric" (scored by an LLM judge) and/or
"checks" (rule-based checks). Returns per-model grades, cost/latency stats, and an
overall verdict. Rate-limited to 3 calls per 8 hours.
Models are "<catalog id>" (OpenRouter) or "<catalog id>@bedrock" / "<catalog id>@vertex" /
"<catalog id>@foundry"; pass matching creds ({"openrouter"?, "bedrock"?, "vertex"?, "foundry"?})
or a bare OpenRouter api_key.
judge_backend picks which backend runs the judge and policy gate.
At most 4 models. priority (balanced|quality|fastest|cheapest) ranks the results;
repeats (1-3) re-sends each prompt for timing accuracy. Returns suggestions (same
provider and backend only), advice, ranking, and best_for_priority, plus a per-run
`cost` total and, per cell, an `evaluation` (answered/quality/instruction_following/
completeness/helpfulness/safety scores, strengths, weaknesses, reasoning, overall).
If the operator has set server-side keys for a backend (see https://github.com/thejaredchapman/evalforge-lite/blob/main/docs/hosting-and-server-keys.md), those are used for it automatically and creds for it are not needed.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
credsNo
modelsYes
api_keyNo
repeatsNo
priorityNobalanced
test_casesYes
judge_backendNoopenrouter

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the 3-calls-per-8-hours rate limit, the 4-model cap, creds/api_key handling, the judge_backend role, and fallback to server-side keys. It stops short of stating cost implications or whether the run persists state, so not a 5.

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?

Purpose is front-loaded and nearly every sentence carries non-obvious operational detail (limits, cred formats, return contents). The prose is dense and somewhat clipped, which hurts scanability, but there is little outright filler beyond the trailing server-keys paragraph.

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

Completeness5/5

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

For a 7-parameter tool with 0% schema coverage and no output schema, the description is remarkably complete: it covers inputs, credential rules, hard limits, and enumerates the returned fields (grades, cost/latency, verdict, suggestions, advice, ranking, best_for_priority, per-cell evaluation). An agent has enough to call it correctly and anticipate results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

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 largely does: model id formats with @bedrock/@vertex/@foundry suffixes, creds/key shape, repeats range (1-3), priority values (balanced|quality|fastest|cheapest, an undeclared enum), and judge_backend semantics are all defined. test_cases internals (rubric/checks) are only loosely described, leaving a small gap.

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 opening sentence gives a specific verb and resource: run a set of test-case prompts against a set of models, scoring each response. This is unmistakably a batch-comparison tool. It does not, however, name or differentiate itself from the overlapping sibling evaluate_prompt, so it stays at 4 rather than 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 framing (comparing multiple models with optional rubric/checks), and hard constraints are given (rate limit, max 4 models, credential requirements). But there is no explicit when-to-use vs evaluate_prompt guidance and no stated exclusions, so the agent must infer which tool to pick.

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

Deploy Server

Other Tools