SALT19 Agent Utility Grid

Model Memory Fit

model-memory-fit

Idempotent

Can this AI model run on my graphics card? Estimate model memory requirements and check whether a quantized LLM fits available GPU VRAM before loading or local inference. Price: $0.05 via x402. Generate one _salt19_operation_id per intended purchase, preserve it across retries, and add _x402_payment_signature after satisfying the challenge. A stable _salt19_operation_id is required and makes semantic retries at-most-once. _salt19_operation_id is recommended but optional for standard x402 compatibility.

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": {
      "parameter_count_b": "<parameter_count_b>",
      "quantization_bits": "<quantization_bits>",
      "vram_gb": "<vram_gb>"
    },
    "name": "model-memory-fit"
  }
}

Input Schema

Name	Required	Description
`vram_gb`	Yes	Input parameter "vram_gb" for the model-memory-fit tool.
`parameter_count_b`	Yes	Input parameter "parameter_count_b" for the model-memory-fit tool.
`quantization_bits`	Yes	Input parameter "quantization_bits" for the model-memory-fit tool.
`_salt19_handoff_id`	No	Optional SALT19 authorization handoff correlation. Preserve the same value across challenge, local signing, and paid retry.
`_salt19_operation_id`	No	Optional but recommended semantic purchase identifier. Generate once per intended purchase and preserve it across challenge, payment, timeout recovery, and retries for the strongest at-most-once contract. Standard x402 clients may omit it.
`runtime_overhead_ratio`	No	Input parameter "runtime_overhead_ratio" for the model-memory-fit tool.
`_x402_payment_signature`	No	Optional x402 PAYMENT-SIGNATURE proof. Omit on the first call to receive the payment challenge; include after satisfying that challenge.

Output Schema

Name	Required	Description
`tool`	No	Canonical SALT19 tool identifier when the result is tool-specific.
`status`	No	SALT19 execution, payment, availability, or verification state.
`response`	No	Tool-specific structured response payload when execution completes.
`operation_id`	No	Client-controlled semantic purchase identifier when applicable.

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 1, 2026

TDQS

A4.2/5.0

Behavior5/5

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

Adds meaningful behavior beyond annotations: payment price, x402 challenge/signature flow, and at-most-once semantics tied to preserving _salt19_operation_id across retries. This deepens the idempotentHint=true annotation without contradicting readOnlyHint=false.

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 description is information-dense and front-loads the purpose, but the x402/payment guidance is somewhat repetitive and the operation-id lines read as contradictory ('required' vs 'recommended but optional'). It earns its place but could be tightened.

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?

The description covers the main purpose, the payment protocol, and retry semantics, while the output schema covers return values and the schema covers parameter definitions. For a tool with 7 params and an output schema, this is largely complete, though it omits guidance on runtime_overhead_ratio and _salt19_handoff_id.

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 coverage is 100%, so the baseline is 3. The description adds semantics for _salt19_operation_id and _x402_payment_signature (generate once, preserve, include after challenge), but it does not clarify the meaning or units of the three required numeric parameters, which have only tautological schema descriptions.

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 description explicitly states it estimates model memory requirements and checks whether a quantized LLM fits available GPU VRAM, with a clear use case ('before loading or local inference'). The verb-resource pairing is specific and none of the sibling tools overlap with this model-memory fit check.

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?

It gives clear context for when to use: before loading or running local inference. It does not name alternatives or exclusions, but none of the listed siblings are obvious substitutes, so the context is sufficient.

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

All SALT19 Agent Utility Grid tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?