Skip to main content
Glama
SOMA AI Emission Factors (SAEF)

SOMA AI Emission Factors (SAEF)

model_class

Resolve a model identifier to its SAEF size class (A small, B mid-size, C large) to estimate inference emissions. Unknown models default to the conservative class C.

Instructions

Return the SAEF model class (A small, B mid-size, C large) for a model identifier.

SOMA AI Emission Factors (SAEF) assign factors by class, not by brand. A model that matches no known pattern gets the conservative class C. Embeddings, image, audio, video and moderation models are out of scope and return an error.

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": {
      "model": "<model>"
    },
    "name": "model_class"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
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 the fallback rule (no pattern match → conservative class C) and the failure mode (out-of-scope model types return an error), both of which affect how an agent should interpret results. It leaves unstated whether the lookup is purely deterministic/local or whether the returned class is an estimate, but the key edge-case behavior is disclosed.

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?

Two tight paragraphs, front-loaded with the return contract and followed by the domain rationale and the error boundary. The parenthetical expansion of A/B/C and the "by class, not by brand" clause both earn their space by preventing misuse.

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 one-parameter, no-output-schema lookup, the definition covers return values, the default/fallback case, and the out-of-scope error case — the three things an agent needs to call it correctly. Only the identifier format and the relationship to the estimation siblings are left implicit.

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

Parameters4/5

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

Schema coverage is 0% and the single `model` parameter is a bare string, so the description must carry param meaning — it does, by framing the value as a "model identifier" that is pattern-matched against known brands, and by defining what happens when no pattern matches. It still never shows an identifier format or example string, which is the one gap an agent could stumble on.

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 and resource ("Return the SAEF model class") and enumerates the possible outputs (A small, B mid-size, C large), so an agent knows exactly what it gets back. It does not name or contrast any sibling tool, but the narrow lookup purpose is unambiguous on its own.

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

Usage Guidelines4/5

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

Gives real scope guidance: factors are assigned by class, not brand, and embeddings/image/audio/video/moderation models "are out of scope and return an error," which tells an agent when not to call it. What's missing is a routing statement — e.g. which sibling to use for the estimation tools instead — so it stops short of explicit alternatives.

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