Skip to main content
Glama

krusch_route_task

Read-onlyIdempotent

Classify coding and reasoning prompts into four routing tiers in under 25µs to match each task with the appropriate local, burst, or frontier model.

Instructions

Classify a coding or reasoning prompt in <25µs into L1_FAST_LOCAL, L2_SWE_MOE, L2_5_BURST_120B, or L3_FRONTIER_REFEREE.

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>"
    },
    "name": "krusch_route_task"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYes
task_typeNo
budget_tierNoauto

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.3.1

TDQS

C2.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the safety profile is covered. The description adds a useful performance trait ('<25µs'), but with no output schema it never says what the call actually returns — a bare label, a confidence, or a decision object — which is the key behavioral fact for a classifier.

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?

A single tightly written sentence with the verb and latency figure front-loaded and zero filler. It is efficient, though the terseness borders on cryptic given the four unexplained tier acronyms.

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

Completeness2/5

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

No output schema, 0% parameter coverage, and an unexplained vocabulary of tier names mean the agent cannot know what to pass in beyond 'prompt' or what the result means for its next action. For a routing decision tool that presumably gates downstream model choice, this is a substantial gap.

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 carry all parameter meaning, yet it mentions none of the three parameters. In particular the 'budget_tier' parameter (default 'auto') and 'task_type' are completely undocumented in both schema and description, leaving the agent unable to use them meaningfully.

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 specific verb ('Classify') and resource ('a coding or reasoning prompt') and names the four output labels, so an agent can tell this is a routing/classification tool rather than a file, git, or context operation. It does not explicitly differentiate itself from siblings like krusch_run or krusch_explain, and the opaque tier names (L2_5_BURST_120B) are never explained.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to call this versus krusch_run or other siblings, and no hint of what the agent should do with the returned tier. The only implied usage is 'before dispatching a prompt,' which the agent must infer entirely.

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