Skip to main content
Glama

MarketAIVerse

by com.marketaiverse
OverviewDiscussionsAdmin

Actually run a small model, right now

try_a_model

Everything else here tells you what a model would do. This one runs one. A 0.8B model on ordinary server CPU answers your prompt live, and the reply carries its own measured tokens/sec for that exact call - not an average someone remembered. It is a weak model and it is often wrong; that is the point, because you get to see what this size actually does instead of reading an adjective for it. One caller at a time: if it is busy you get a number of seconds rather than a queue, because two callers on one CPU brain roughly halve each other's speed. Needs no identity, costs no credits. Read-only in the sense that it changes nothing here: it runs a small model and gives you the text back. It costs us real compute, so it is rate limited, and when the box is busy it says so instead of queueing you.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesWhat to ask it. Keep it short - a long prompt costs more CPU to read than the answer costs to write.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changed
    • removedInput schema / properties / intrebare
      Removed value: -{
-  "description": "What to ask it. Keep it short - a long prompt costs more CPU to read than the answer costs to write.",
-  "type": "string"
-}
    • addedInput schema / properties / prompt
      Added value: +{
+  "description": "What to ask it. Keep it short - a long prompt costs more CPU to read than the answer costs to write.",
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "intrebare"
-]New value: +[
+  "prompt"
+]
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations provided, the description carries the full burden of disclosure. It reveals rate limiting, single-caller-at-a-time behavior, the busy response in seconds, credit/identity requirements, CPU-based slowdown reasoning, and read-only semantics. This is unusually thorough for a real compute-running tool.

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?

The description is long and somewhat rambling, but nearly every sentence adds a distinct non-obvious behavioral fact: live tokens/sec, weak model rationale, concurrency impact, auth/cost, and rate limits. The core purpose is front-loaded, but the paragraph structure could be tightened without losing information.

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 simple one-parameter tool with no output schema, the description is remarkably complete. It explains what the response contains, what happens when busy, that no identity is needed, and that rate limiting exists. An agent would know what to expect from the call and its result.

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?

The schema already documents the single 'prompt' parameter at 100% coverage. The description adds useful extra semantics: keep the prompt short because reading a long prompt costs more CPU than writing the answer. That goes beyond schema, though the key guidance is only lightly embedded in the description.

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 clearly states a specific action: it runs an actual small 0.8B model on CPU and returns the live reply with measured tokens/sec. It explicitly contrasts itself with every other tool in the workspace ('Everything else here tells you what a model would do. This one runs one.') This makes differentiation from siblings immediate and concrete.

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

Usage Guidelines5/5

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

The description gives clear when-to-use context: use it to see what a weak model actually does rather than trusting a summary, and it warns that the model is often wrong. It also tells the caller about exclusivity, rate limiting, and cost behavior, so an agent knows when this is appropriate and what conditions to expect.

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

All MarketAIVerse 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