Skip to main content
Glama
Sign In
Local Model MCP

Local Model MCP

by Doughboyfressh
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

create_tensor_asset

Save named float32 arrays (up to 1M values) as tensor assets for replacement, additive, or low-rank checkpoint edits; use safetensors files for larger assets.

Instructions

Save named float32 arrays for replacement, additive, or low-rank edits. Max 1M values.

Example: tensors={"left": [[1.0], [0.0]], "right": [[0.1, 0.2]]}. For larger assets, place a safetensors file directly in workspace/tensors (max 256 MiB).

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": {
      "asset": "<asset>",
      "tensors": "<tensors>"
    },
    "name": "create_tensor_asset"
  }
}

Input Schema

NameRequiredDescriptionDefault
assetYes
tensorsYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.1

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare this is a non-read-only, non-destructive, closed-world write, and the description adds real constraints (1M values inline, 256 MiB for files) plus supported edit modes. It omits the highest-risk behavior for a create tool: what happens if `asset` already exists (overwrite, error, versioning), which matters even with destructiveHint=false.

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 short sentences plus one example line, with the size limit front-loaded and the overflow path last. No filler; the example earns its space by disambiguating the nested tensors shape.

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?

An output schema exists, so return values need not be explained, and the size/format guidance covers invocation. However, for a create tool with an identifier parameter and 0% schema coverage, the missing collision/overwrite semantics leave an agent unable to predict the outcome of a repeated call.

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 description coverage is 0%, so the description must carry the load. It does a good job on the harder `tensors` parameter, giving a concrete nested example that reveals the name→array mapping and nesting shape, but says nothing beyond 'named' about `asset` other than the regex pattern already in the schema.

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+resource: save named float32 arrays, with the intended use (replacement, additive, or low-rank edits) and hard limits. It clearly is not a read tool like read_tensor nor an applier like apply_weight_edits, though it never names a sibling explicitly.

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?

Gives one concrete routing rule for the size alternative: above the inline limit, place a safetensors file in workspace/tensors. Beyond that it offers no when-to-use vs when-not guidance, and no prerequisites for the named asset (e.g., whether it must exist already).

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