DZ23 Subagents Universal MCP

Explain model routing

routing_explain

Read-onlyIdempotent

Explains the current model selection order for a given task type, detailing why alternatives are skipped based on cost, eligibility, cooldowns, success/latency metrics, and provider quotas—without making any provider calls.

Instructions

Which models the server would use for a task type right now, in order, and why others are skipped: cost tier, eligibility, cooldowns, observed success and latency, quota from provider headers. No provider calls.

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": "routing_explain"
  }
}

Input Schema

Name	Required	Default
`role`	No	worker
`target`	No	auto
`task_type`	No

Schema Changelog

Changes observed during successful MCP inspections.

Addedv4.3.0Sep 17, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare readOnly, idempotent, and non-destructive behavior. The description adds valuable behavioral context: it explicitly states 'No provider calls' (consistent with readOnly) and lists the factors considered (cost tier, eligibility, cooldowns, success/latency, quota from provider headers), which gives insight into what affects the result. It does not contradict annotations.

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, well-structured sentence that front-loads the core purpose and then lists the factors considered. There is no wasted wording; it is concise and informative.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only, idempotent tool with no output schema, the description covers the main purpose and behavioral constraints but lacks details on the output structure and parameter semantics for role and target. It is adequate for basic understanding but not fully complete for correct invocation without additional inference.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must explain the parameters. It only mentions 'task type' (which maps to task_type) but gives no information about role or target parameters. The description does not compensate for the lack of schema descriptions; an agent would be unsure what role and target do or how they affect the routing explanation.

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 clear purpose: it returns the ordered list of models the server would use for a given task type right now, with reasons for skipping others. It differentiates itself from siblings like list_models and provider_inventory by focusing on the routing decision and explicitly noting 'No provider calls'.

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?

The description implies usage: it is for explaining current routing decisions and does not make external calls. However, it does not explicitly state when to use this tool versus alternatives (e.g., list_models, discover_models) or provide any exclusion criteria. The context is clear but not explicit about alternative selection.

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