DZ23 Subagents Universal MCP

Verify model inference (billable)

verify_model

Proves inference access for a provider:model by running one minimal, non-sensitive generation; requires confirm_billable=true and may consume credits.

Instructions

Run one minimal, non-sensitive generation against provider:model to prove inference access. Requires confirm_billable=true, may consume credits, never runs automatically, never retries or fails over.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "target": "<target>",
      "confirm_billable": "<confirm_billable>"
    },
    "name": "verify_model"
  }
}

Input Schema

Name	Required	Description
`target`	Yes	provider:model to verify; it does not need to be in the rotation.
`timeout_ms`	No	Timeout for the single generation.
`confirm_billable`	Yes	Must be true: acknowledges that this call may be billed.
`max_output_tokens`	No	Output token cap for the generation. The default leaves enough room for reasoning models to emit their final reply.

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedv4.4.0Nov 5, 2026

changedInput schema / properties / max_output_tokens / default
```
Previous value: -8New value: +128
```

changedInput schema / properties / max_output_tokens / description

Previous value: -"Output token cap for the generation."New value: +"Output token cap for the generation. The default leaves enough room for reasoning models to emit their final reply."

changedInput schema / properties / max_output_tokens / maximum
```
Previous value: -32New value: +512
```

Addedv3.0.0Sep 15, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the annotations (readOnlyHint=false, openWorldHint=true, idempotentHint=false), the description discloses the cost consequence ('may consume credits'), the no-retry/no-failover semantics, and the manual-invocation guarantee. These are exactly the behavioral facts an agent needs before triggering a billable external call.

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?

Two compact sentences with zero filler: the action and target come first, followed by the billing precondition and the retry/auto-run guarantees. Every clause carries distinct operational information.

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 no output schema, the description might ideally say what a successful verification yields (e.g., confirmation, latency, sample output), and it does not. Still, for a single-call probe with fully documented parameters and rich behavioral notes, an agent has enough to invoke it correctly.

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%, so the schema already documents target, timeout_ms, max_output_tokens, and confirm_billable, including the note that target need not be in the rotation. The description only restates the confirm_billable=true requirement, adding no syntax or format detail beyond the structured fields; 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 names a specific verb and resource ('Run one minimal, non-sensitive generation against provider:model') and states its purpose ('to prove inference access'), which cleanly separates it from siblings like list_models, discover_models, and health_check that never touch a provider.

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?

It gives clear context for use ('to prove inference access') and a hard precondition (confirm_billable=true) plus the reassurance that it 'never runs automatically,' which tells the agent this is an explicit, deliberate call. It stops short of naming an alternative or an explicit when-not-to-use case (e.g., prefer health_check for a free liveness probe).

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