Skip to main content
Glama
Sign In
t2000

t2000

by t2000-afi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

t2000_chat

Send prompts or message lists to a private, OpenAI-compatible inference API with ZDR or GPU-TEE confidentiality for protected AI processing.

Instructions

Run private inference on Audric Private Inference at api.audric.ai (OpenAI-compatible; ZDR by default, a phala/* tier is GPU-TEE confidential), billed to the user's Audric credit. Requires T2000_API_KEY in the server env — mint one at audric.ai (minting requires $5 of credit). Pass a single prompt, or a full messages list. Discover model ids with t2000_models; defaults to the fast gpt-oss-120b.

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": "t2000_chat"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNoModel id (default openai/gpt-oss-120b; see t2000_models)
promptNoUser prompt (shorthand for a single user message)
messagesNoFull message list (overrides `prompt` when present)
maxTokensNoMax output tokens
temperatureNoSampling temperature (0–2)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv10.14.1
  2. Removedv10.13.4
  3. Addedv9.12.0
  4. Removedv9.8.0
  5. Changed1 schema field changedv5.24.1
    • changedInput schema / properties / model / description
      Previous value: -"Model id (default zai/glm-5.2; see t2000_models)"New value: +"Model id (default openai/gpt-oss-120b; see t2000_models)"
  6. Addedv5.15.1

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden of behavioral disclosure. It reveals important traits: private inference with ZDR default, GPU-TEE confidentiality for specific tiers, billing to user credit, and the T2000_API_KEY requirement. It does not mention rate limits or error cases, but the disclosed privacy and billing specifics go beyond a generic 'chat' description.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact paragraph with no redundant statements. Every sentence contributes value: privacy, billing, authentication, input modes, and model discovery. It is front-loaded with the primary action and remains efficiently structured for an AI agent to parse.

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 relatively simple inference tool with no output schema, the description covers all essential context: what it does, where it runs, how it is billed, what is required to use it, how to pass inputs, and how to choose a model. It even mentions the default model. The absence of an explicit output description is mitigated by the tool's simplicity and the lack of an output schema.

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 coverage is 100%, so the baseline is 3, but the description adds meaningful semantics beyond the schema: it clarifies that 'prompt' is shorthand for a single user message while 'messages' is a full list, and that 'model' defaults to a specific fast model and can be discovered via t2000_models. This relationship between parameters is not fully captured in the schema alone.

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 uses the verb 'Run' with the resource 'private inference' and specifies the endpoint (api.audric.ai), clearly defining the tool's function. It also notes OpenAI compatibility and the default model, making it distinct from sibling t2000_* tools which are primarily payment/job/service-related.

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 description provides clear usage context: it explains how to pass a prompt or messages list, mentions the prerequisite API key and credit, and points to t2000_models for model IDs, indicating when to use that sibling tool. It does not explicitly state when *not* to use this tool, but the context is sufficient for an agent to select it for chat/inference tasks.

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