Skip to main content
Glama

body_local_models

Select local models compatible with your machine's free RAM; ranks verified options by measured memory and filters by role, censorship, or language, never suggesting models that won't fit.

Instructions

The local-model catalogue and what THIS machine can run.

Sizes and SHA-256 are the published ones, so a download can be verified before it is used. The ranking uses the measured free RAM - it never suggests a model that would not fit. Nothing is downloaded: you choose, you fetch it, you point BODY_MCP_LOCAL_MODEL at it.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "body_local_models"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNoworker
uncensoredNo
multilingualNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.4.0

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 does meaningful work: it states nothing is downloaded (so the call is effectively read-only despite being a catalogue for downloads), that published sizes and SHA-256 allow verification, and that ranking is grounded in measured free RAM and never proposes a model that would not fit. That is exactly the kind of context annotations would otherwise supply; only latency, caching and whether local disk is scanned are left unstated.

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?

Four short sentences, front-loaded with what the tool is, then verification, then ranking logic, then the crucial 'nothing is downloaded' caveat. Every sentence carries distinct information and none repeats the schema or annotations.

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 zero-required-parameter catalogue with no output schema, the description explains the concept of the result (catalogue plus a fit ranking) but not its shape, and it leaves three filter parameters entirely unexplained. It is adequate to decide whether to call the tool, but not adequate to call it with the intended filters.

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% and three parameters (role, uncensored, multilingual) exist with only bare type/default declarations. The description never mentions these filters or what they change in the ranking, so an agent cannot tell whether 'role' selects a model category or alters the fit scoring. The RAM-based ranking sentence is the only behavioural hint and it does not map to any parameter.

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?

It names the resource precisely ('the local-model catalogue') and adds a scope qualifier ('what THIS machine can run'), which separates it conceptually from a generic model list. The verb is implicit (list/rank rather than an action), and it never explicitly distinguishes itself from the sibling body_models, so it stops short of a 5.

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 closing line implies the usage flow: consult this to choose, then fetch the file yourself and set BODY_MCP_LOCAL_MODEL. That is real guidance about what happens after the call, but there is no explicit when-to-use-vs-alternative statement and no exclusion telling the agent when another catalogue tool is the right pick.

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