Skip to main content
Glama

arobi_classify_and_route

Classify a prompt and select the lowest-cost model route that meets required capabilities, flagging any premium justified by quality_exception policy before execution.

Instructions

Classify a prompt and choose the cheapest route capable of the work from your candidate set, reporting whether any cost above the cheapest capable route is justified by required_capabilities or an explicit quality_exception policy. Set record=false to preview without appending to the local chain.

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": {
      "prompt": "<prompt>",
      "candidates": "<candidates>"
    },
    "name": "arobi_classify_and_route"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYesPrompt text to classify and route.
recordNoDefault true. Set false to evaluate without sealing a chain record.
candidatesYesCandidate models with id/model, cost_per_1k_prompt_usd, cost_per_1k_completion_usd, capabilities, observed_success_rate, and observed_sample_size.
quality_exceptionNoOptional policy allowing a higher-cost route only when its observed success rate beats the cheapest capable route by min_success_uplift with at least min_sample_size samples on each side.
required_capabilitiesNoCapabilities a candidate must advertise to be considered capable.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.5/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose the important side effect (appending a sealed record to the local chain unless record=false), which is the key behavioral trait, but it says nothing about permissions, failure modes, cost-model assumptions, or what the report contains beyond the premium decision.

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?

Two dense sentences, front-loaded with the core action and ending with a useful operational toggle. It is efficient, though the second sentence is packed with policy jargon that could be split for readability.

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 five-parameter tool with nested objects and no output schema, the description conveys the decision logic, the chain-write side effect, and the preview mode, and it sketches what gets reported. It still omits the concrete response shape, which matters more given the absence of an output schema.

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 each parameter is already documented. The description reinforces the record=false preview behavior and the quality_exception premium rule, but adds no syntax, units, or edge-case meaning 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 concrete verb and resource: classify a prompt and choose the cheapest capable route from the candidate set, plus report whether a cost premium is justified. An agent can tell this apart from the sibling tools (route_grant, authorize, verify_chain), though the description never names a sibling to reinforce the distinction.

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?

Implies the usage context (routing a prompt against candidates) and gives a conditional hint that record=false previews without chain writes. It offers no explicit when-not-to-use guidance, no prerequisites, and no routing to alternatives for classification-only or verification needs.

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