Skip to main content
Glama
SpiceMCP
by oniondas

start_optimization

Creates a saved optimization run for an LTspice circuit by defining parameters, goals, and optional limits; rejects specs that cannot be met.

Instructions

Create a saved optimization run. netlist uses {NAME} for each param and a .meas line per metric. Refused if the spec is impossible.

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": {
      "run_id": "<run_id>",
      "netlist": "<netlist>",
      "params": "<params>",
      "goals": "<goals>"
    },
    "name": "start_optimization"
  }
}

Input Schema

NameRequiredDescriptionDefault
goalsYes
limitsNo
paramsYes
run_idYes
netlistYes
circuit_typeNogeneral

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.1.0

TDQS

B3.1/5.0
Behavior2/5

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

With no annotations, the description carries the full behavioral burden. It does disclose one real behavior (rejection of impossible specs) but says nothing about persistence semantics of a "saved" run, whether it executes immediately, required permissions, or how run_id relates to later query_run calls. For a 6-parameter creation tool this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences with the core action front-loaded and no filler. The middle sentence is telegraphic and slightly hard to parse ("a .meas line per metric"), which costs a point.

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 mutation tool with six parameters, four required, no annotations, and no output schema, the description leaves the majority of the contract unexplained: circuit_type's role, how limits interact with goals, and what a caller gets back. Only the netlist format and failure mode are covered.

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 effectively 0% at the top level, and the description only indirectly explains params (via {NAME} substitution) and metrics (via .meas). It adds no meaning for run_id, circuit_type, limits, or the min/max/values alternatives on Param.

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?

"Create a saved optimization run" gives a specific verb and resource, and the netlist templating note hints at what makes this tool distinctive. It never names the closely related run_optimization or start_from_template, so the boundary with those siblings must be inferred.

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 phrase "Refused if the spec is impossible" implies you should validate first, but the description never points at check_feasibility or check_setup, nor does it say when to prefer start_from_template or run_optimization over this call. Usage is only loosely implied.

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