Skip to main content
Glama
Sign In
Nanites

Nanites

by ADn-001
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Unload Model

unload_model

Free up memory and resources by unloading a model instance from your LM Studio endpoint using its instance ID. Specify the instance_id to release the model and reduce load.

Instructions

Unload a loaded model instance by its instance_id from the active profile's LM Studio endpoint.

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": {
      "instance_id": "<instance_id>"
    },
    "name": "unload_model"
  }
}

Input Schema

NameRequiredDescriptionDefault
instance_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It implies a state-changing operation (unloading) but does not disclose potential side effects like freeing memory, whether the operation is reversible, or whether it affects other instances. It also doesn't mention errors when instance_id is not loaded. This is a significant gap for a mutation tool.

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?

The description is a single sentence with zero fluff, front-loading the verb and resource. It is appropriately concise for a simple operation with one parameter.

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?

For a single-parameter tool with no output schema and no annotations, the description is minimal. It lacks critical context such as how to find instance_id (likely from list_models or get_loaded_model), what to expect in response, and error handling. Given the tool's low complexity, a slightly richer description would be sufficient, but the current one leaves gaps.

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?

The schema has only one parameter (instance_id) with no description, and schema coverage is 0%. The description mentions instance_id but does not explain what an instance_id is or how to obtain it. At 0% coverage, the description should compensate, and it only barely does by mentioning 'loaded model instance' – leaving the agent uncertain about the ID format.

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 clearly states the action (unload a model) and the target resource (a loaded model instance by instance_id) from the active profile's LM Studio endpoint. It distinguishes itself from load_model and get_loaded_model by specifying unload semantics, but it could be more explicit about the distinction from 'get_loaded_model' which is about querying, not modifying.

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?

The description provides no guidance on when to use this tool versus alternatives like load_model or get_loaded_model. It doesn't state prerequisites (e.g., model must be loaded, instance_id must be valid) or consequences. An agent would have to infer usage from the name alone.

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

Deploy Server

Other Tools