Skip to main content
Glama

Arobi Immaculate MCP

arobi_classify_and_route

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 a named required capability, by measured quality under your explicit quality_exception policy, or by nothing. Also reports whether this work was already done. Set record=false to preview without writing to your ledger.

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
promptYes
recordNoDefault true. false = answer without sealing.
candidatesYesRoutes with cost_per_1k_prompt_usd, cost_per_1k_completion_usd, capabilities, observed_success_rate, observed_sample_size.
quality_exceptionNoOptional. The only way a dearer route is chosen: its measured success must beat the cheapest capable route by min_success_uplift (0-1] with at least min_sample_size recorded runs on each side, optionally capped by max_premium_usd.
required_capabilitiesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does substantial work: it discloses that the default behavior writes to a ledger (record defaults to true), offers a preview escape hatch, and explains the only sanctioned reason for choosing a dearer route (measured success uplift versus the cheapest capable route). It also mentions detecting whether the work was already done, which is meaningful idempotency behavior. It does not describe failure modes or permission requirements, keeping it short of a 5.

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

Conciseness3/5

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

The definition is short and front-loads the core action, and the preview sentence is efficient. But the opening sentence chains three parallel justification clauses plus 'or by nothing,' which is grammatically strained and forces a re-read to parse the decision rule. Information density is high, but readability suffers.

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 five-parameter tool with a nested object and no output schema, the description should explain the reported result, since the tool's stated job is to 'report' three distinct things. It hints at those outputs but never describes their form, and it omits what happens when no candidate is capable or when data is insufficient for the quality_exception test. Adequate for the decision logic, incomplete for the return contract.

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 coverage is 60%, with candidates and quality_exception carrying their own field-level documentation, so the baseline is around 3. The description adds real meaning by framing required_capabilities as 'named required capability' and clarifying that quality_exception is the only path to a premium route. However, it adds nothing about the shape or content of prompt beyond classification, and the nested quality_exception thresholds are already fully documented in 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?

The description states a specific compound action: classify a prompt, pick the cheapest capable route from a candidate set, and report whether any cost premium is justified. That is clearly distinct from the sibling tools (authorize, route_grant, verify_chain), which are about permissioning and verification rather than cost-aware routing. It falls short of a 5 only because the three reporting outcomes are packed into one long clause rather than enumerated cleanly.

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 only explicit usage instruction is 'Set record=false to preview without writing to your ledger,' which tells the agent how to do a dry run. There is no statement of when this tool should be chosen over arobi_authorize or arobi_route_grant, or what prerequisites (e.g. an existing ledger, candidate set construction) must hold. Usage is implied by the routing framing rather than spelled out.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.