Skip to main content
Glama

ai-netcafe

by com.ainetcafe
OverviewDiscussionsAdmin

Run the same prompt on several models and compare

compare_models

Run one prompt across multiple LLMs in parallel and return every answer side by side with measured platform cost metadata and latency. The beta platform covers the user charge ($0.00). This answers "which model should I actually use for this kind of task?" with data instead of guesswork. Example — GET https://ainetcafe.com/t/compare_models?prompt=Explain+CAP+theorem+in+1+line

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modelsNoModel ids to compare (2-5). Defaults to a cheap/mid/strong spread.
promptYesThe prompt to send to every model.
systemNoOptional system instruction applied to all.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultsYes
summaryNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "results": {
+      "items": {
+        "type": "object"
+      },
+      "type": "array"
+    },
+    "summary": {
+      "type": [
+        "object",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "results"
+  ],
+  "type": "object"
+}
  2. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations only say readOnlyHint=false and destructiveHint=false; the description goes beyond that by disclosing parallel fan-out, side-by-side return shape, latency and cost metadata, and the beta-platform $0.00 user charge. It stops short of stating rate limits or model-count constraints explicitly, and doesn't mention that 'models' is mutually exclusive with defaults.

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?

Front-loaded with the core verb and outcome, then cost/latency and finally the example URL. The example is valuable but adds a fourth sentence of length; still, every sentence carries information and none is filler.

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 an output schema present, return-shape details are already covered, and the description covers the otherwise-missing behavioral traits (parallelism, metadata, billing). What's left unaddressed is the interaction with the 'models' default vs. explicit list and any per-call concurrency limits, minor for a read-only beta tool.

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 coverage is 100% – each of the three parameters already has a description covering defaults and semantics. The description adds no extra parameter detail (no model-id format, no system-prompt merging behavior), so it correctly sits at the baseline for a fully documented 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?

States a specific verb+resource ('run one prompt across multiple LLMs in parallel') with the distinctive scope of fan-out comparison. It clearly contrasts with sibling ask_model (single model), list_models (enumeration), and model_costs (pricing lookup), so an agent can route without opening a schema.

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?

The framing 'which model should I actually use for this kind of task?' gives a clear task context for when to reach for this tool, and the inline example query demonstrates invocation. It doesn't state explicit exclusions or name alternatives like ask_model for single-model runs, which keeps it short of a 5.

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

All ai-netcafe toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources