Context Studios MCP

Get Local AI Quality (Terminal-Bench-Mini)

get_local_ai_quality

Read-only

Agentic quality results for local models from Terminal-Bench-Mini (core19) by kyuz0, Apache-2.0: pass rate within attempts and pass@1 per model/quant/hardware, each with the run URL. Returned with the required attribution.

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": "get_local_ai_quality"
  }
}

Input Schema

Name	Required	Description	Default
`platform`	No	Hardware platform

Output Schema

Name	Required	Description
`data`	No	Structured result payload. Present for responseFormat='v2' tools.
`meta`	No	Result metadata such as count, locale fallback, cache scope, or response format.
`count`	No	Number of returned records for list and search tools.
`error`	No	Human-readable error message when success is false.
`success`	No	Whether the tool call completed successfully.

Schema Changelog

Changes observed during successful MCP inspections.

AddedOct 1, 2026

TDQS

B3.2/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds a genuinely useful behavioral note: the result carries a required attribution, implying license/attribution obligations on use. Beyond that it adds little about caching, freshness, or empty-result behavior.

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?

A single dense sentence, front-loaded with the resource and dataset before the metrics. It is slightly jargon-heavy but every clause (dataset, metrics, run URL, attribution) earns its place with no 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?

An output schema exists, so return-value detail is not required, yet the description still names the key metrics and per-dimension grouping. Combined with the attribution note, an agent has enough to invoke and interpret the call; only the optional-parameter behavior is left implicit.

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 the single platform parameter has a full enum, so the schema does the work. The description mentions 'per model/quant/hardware' but never explains the platform filter or what happens when it is omitted (it is optional), so it adds nothing beyond the schema.

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?

States a specific verb and resource (agentic quality results for local models) plus the source dataset (Terminal-Bench-Mini core19) and the exact metrics returned (pass rate within attempts, pass@1). Clear enough to tell apart from siblings like list_local_ai_hardware or get_local_ai_creator, though it never names an alternative explicitly.

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

Usage Guidelines2/5

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

No when-to-use or when-not-to-use guidance, and no alternative tool is referenced. The agent must infer that this is the tool for model benchmarking data versus, say, list_local_ai_recipes or get_local_ai_methodology.

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

All Context Studios MCP 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?