Clearbar model verdicts

List verdicts: which model is cheapest for each task

list_verdicts

Read-onlyIdempotent

Which LLM is the cheapest that still passes? Lists every published Clearbar verdict: the task, the pass bar, the cheapest passing model, its cost per successful task (retries and failures counted) and the page to check it. Optional filter by task type.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "list_verdicts"
  }
}

Input Schema

Name	Required	Description	Default
`task`	No	Only verdicts of this task type, for example classification, extraction or tool-call.

Output Schema

Name	Required	Description
`count`	Yes	Number of verdicts returned.
`app_url`	Yes	Where to run the same verdict on your own examples.
`app_note`	Yes
`verdicts`	Yes
`prices_as_of`	Yes	Date (YYYY-MM-DD) of the newest price snapshot behind the figures.

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A3.7/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and a closed-world scope, so the safety profile is fully covered. The description adds two useful behavioral facts beyond that: only *published* verdicts are returned, and cost is measured per successful task with retries and failures counted. It says nothing about ordering, result count, or pagination, which a list tool would benefit from.

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 leading question is an effective hook and the enumeration of returned fields is information-dense rather than padded. Slightly long, and some of that field enumeration duplicates the output schema, but nothing is genuinely wasted.

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?

For a one-optional-param, read-only list tool with an output schema and full annotations, the definition covers scope, filtering, and cost semantics well. The remaining gap is operational: no indication of ordering or how many verdicts come back, which matters for an unfiltered list of "every published" verdict.

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% and there is a single optional `task` parameter whose schema entry already gives examples (classification, extraction, tool-call). The description's "Optional filter by task type" merely restates that, adding no new meaning; baseline 3 applies.

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 specific verb and resource ("Lists every published Clearbar verdict") and then enumerates exactly what each verdict contains: task, pass bar, cheapest passing model, cost per successful task, and source page. A distinct framing question ("Which LLM is the cheapest that still passes?") makes the tool's purpose unambiguous and separable from get_verdict.

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 only implied: "Lists every published" plus an optional task-type filter suggests bulk browsing rather than single-record retrieval, which is what the sibling get_verdict presumably does. The description never names the alternative or states a condition such as "use get_verdict when you already know the task."

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

All Clearbar model verdicts tools Inspect

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

Need Help?