Skip to main content
Glama

ai-bom-license-resolver

AI-BOM License Chain Resolver for Hugging Face Models — Walks the Hugging Face lineage of up to 10 models (base_model chain, training datasets; at most 30 nodes, 4 generations) and applies a curated, hash-pinned table of license clauses (Apache-2.0, MIT, CC-BY, CC-BY-NC, CC-BY-SA, OpenRAIL variants, Llama 2 / 3 / 3.1 / 3.2 / 3.3, Gemma, Mistral Research License) to each intended use: commercial or not, API, weights or on-prem, fine-tuning, monthly acti

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": {
      "models": "<models>",
      "uses": "<uses>"
    },
    "name": "ai-bom-license-resolver"
  }
}

Input Schema

NameRequiredDescriptionDefault
usesYesIntended uses to decide, each evaluated independently.
modelsYesHugging Face model repo ids (owner/name) used together in the system.
datasetsNoExtra Hugging Face dataset repo ids; datasets named on the model cards are followed automatically.
dataset_termsNoadvisory (default): a dataset license restriction yields UNDETERMINED because it is unsettled whether it binds trained weights. binding: treat it as binding and report CONFLICT.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the behavioral burden and does a decent job: it discloses traversal caps (10 models, 30 nodes, 4 generations), that the clause table is curated and hash-pinned (deterministic, not free-form LLM judgment), and that each use is decided independently. It does not say whether it fetches live from Hugging Face (network/auth/rate limits) or what verdict values are emitted, and the text is cut off mid-clause, leaving the behavioral picture incomplete.

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?

The content is dense and every clause carries real information, but it is delivered as one long em-dash run-on and, critically, truncates mid-word ('monthly acti'), so a key operand and whatever followed are simply missing. Front-loading is good; structure and completeness of the sentence are not.

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 tool this complex — four parameters, a nested per-use object with nine fields, advisory-vs-binding dataset semantics — the description covers inputs well but, with no output schema and no annotations, it never explains the shape of the results (compliance verdicts, per-use breakdown) and the truncated tail removes information. An agent could call it, but cannot anticipate the response.

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 100%, so every parameter, enum and nested field is already documented in the input schema. The description restates a subset of those dimensions (commercial, API, weights/on-prem, fine-tuning, monthly active users) without adding format, default or interaction semantics beyond the schema, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The name plus the opening line state a specific verb (walks the model lineage, applies license clauses) and a specific resource (Hugging Face base_model chain and training datasets), scoped to per-intended-use evaluation. The named license families and the constraints (10 models, 30 nodes, 4 generations) make it clearly distinct from a simple license-identifier sibling.

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 description implies when the tool is appropriate — deciding license obligations across a model lineage for a set of intended uses — but never states when to prefer it over the sibling 'license-identify', nor any prerequisites or exclusions. Usage must be inferred from the operand list.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources