Skip to main content
Glama

select_frugal_model

Selects a model by task reversibility: recommends frugal models for mechanical reversible work and a prep-then-execute protocol for irreversible architectural decisions.

Instructions

Dynamically routes tasks based on Bezos Type-1 (irreversible) vs Type-2 (reversible) doors. Recommends frugal sub-cent models (Gemini 3.8 Flash, local models) for mechanical tasks, or the 2026 Sandwich Protocol (prep <600 tokens -> Claude Opus 5.5 / Claude Fable / o3 / DeepSeek-R1 -> Flash exec) for irreversible architectural decisions.

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": {
      "task_kind": "<task_kind>"
    },
    "name": "select_frugal_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
heavinessNoReasoning heaviness (0.0 to 10.0, default: 5.0).
task_kindYesTask descriptor (e.g. 'lint_check', 'refactor', 'deploy_db', 'fix_security_flaw').general
importanceNoStrategic importance (0.0 to 10.0, default: 5.0).
is_irreversibleNoTrue for Bezos Type-1 irreversible one-way doors.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.2.0

TDQS

B3/5.0
Behavior2/5

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

No annotations are supplied, so the description carries the full behavioral burden and does not meet it. It never states whether the tool is advisory only (i.e., returns a recommendation without invoking any model), whether it has side effects or costs, or whether it is deterministic — all critical for a 'routing' tool whose name could imply execution.

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?

Two sentences, front-loaded with the routing logic, so there is little filler. But the second sentence is a dense run-on that piles on unexplained proper nouns ('2026 Sandwich Protocol', 'Claude Opus 5.5', 'Claude Fable', 'Flash exec'), which costs clarity without adding actionable meaning.

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?

With no annotations and no output schema, the description must explain what the tool returns — a model name, a routing label, a prompt template? — and it does not. For a four-parameter routing tool whose entire value is the returned recommendation, this leaves a major gap an agent cannot resolve from structured fields alone.

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 100%, so the four parameters are already self-documented, establishing a baseline of 3. The description adds conceptual meaning to is_irreversible by tying it to Bezos Type-1/Type-2 doors, but leaves heaviness and importance entirely to the schema and does not explain how the parameters combine to produce a routing decision.

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 names a concrete function: routing/selecting models based on task reversibility, with two named routing paths (frugal models vs. the 'Sandwich Protocol'). It is distinguishable from siblings like check_circuit_breaker or compress_terminal_log, though the heavy jargon and exotic model names (Gemini 3.8 Flash, Claude Fable) read more like marketing than a precise purpose statement.

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?

It does describe internal routing rules — mechanical tasks get frugal models, irreversible architectural decisions get the prep-plus-reasoning-model protocol — which implies when its output is appropriate. However, it never says when an agent should call this tool versus just picking a model itself, nor does it reference any sibling tool as an alternative.

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