Skip to main content
Glama

new_circuit

Create a complete circuit file from a part list and netlist in one call, with optional board placement; invalid input is rejected and nothing is written.

Instructions

Write a whole new circuit file from a netlist in one call: parts (no positions) and nets (pin lists). Unless place is false the board is then placed (fitted when no board is given) as a second entry. A block used more than once goes in sheets, used by instances. Nothing is written if anything is wrong; the answer says what. An existing file is refused unless replace. Details: guide { topic: "writing-circuits" }.

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": {
      "file": "<file>",
      "parts": "<parts>",
      "nets": "<nets>"
    },
    "name": "new_circuit"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYese.g. power.circuit.tsx
netsYese.g. { "GND": ["R1.pin2", "U1.GND"] }
boardNomm; default 30 x 20
holesNo
pagesNoPages after "Main", which holds the rest
partsYesMay be empty when instances make them
placeNoDefault true
poursNo
sheetsNoEach written as <name>.sheet.tsx
replaceNo
instancesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations at all, the description carries the full burden and does substantial work: it discloses the transactional guarantee ('Nothing is written if anything is wrong; the answer says what'), the refusal on existing files without replace, the automatic post-placement pass, and the default board-fitting behavior. It does not discuss permissions, size/performance limits, or what the error payload looks like beyond 'the answer says what'.

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?

Front-loaded with the core action, then ordered by workflow (placement, reuse via sheets, atomicity, overwrite guard, pointer to guide). Dense but nearly every clause carries information; 'A block used more than once goes in sheets, used by instances' is slightly compressed to the point of ambiguity.

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?

For an 11-parameter, deeply nested mutation tool with no annotations and no output schema, the description covers the call shape, side effects, failure semantics, and a documentation escape hatch. The remaining gaps (holes, pours, pages, and the exact error response) are largely covered by the input schema or by the referenced guide topic.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

At 64% schema coverage across 11 parameters, the description adds real meaning: parts carry no positions, nets are pin lists, place defaults to true and triggers a second placement entry, board is optional and triggers fitting when omitted, and sheets/instances model reused blocks. It leaves holes, pours, and pages entirely to the schema, which is a reasonable omission given those have their own 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?

Opens with a specific verb and resource — 'Write a whole new circuit file from a netlist in one call' — and immediately names the two core inputs (parts, nets). The words 'whole new' plus 'An existing file is refused unless replace' separate it cleanly from edit_circuit without needing to name it.

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?

Establishes the use case (bulk creation from a netlist rather than incremental edits) and states the precondition for touching an existing file ('refused unless replace'). It also routes to guide { topic: "writing-circuits" } for detail, but never explicitly names edit_circuit as the alternative for modifying an existing board, leaving that inference to the agent.

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