Skip to main content
Glama
mo9652962-ai

circuit-agent

by mo9652962-ai
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

synthesize_circuit

Read-onlyIdempotent

Convert a natural-language hardware prompt into a deterministic netlist and component modules for MCU boards such as STM32, ESP32, RP2040, and ATmega328P.

Instructions

Synthesize a deterministic hardware netlist and component modules from a natural language prompt. Supported MCUs: STM32F103, ESP32-C3, ESP32-S3, RP2040, STC89C52, CH32V003, STM32G030, ATmega328P. Peripherals: Type-C, LDO, Crystal, Buttons, LEDs, Buzzer, I2C, RS485, CAN, TP4056 Battery, AHT20 Temp/Humidity Sensor, MPU6050 6-Axis Motion Sensor.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
promptYesNatural language circuit description, e.g. '基于 CH32V003 的 AHT20 温湿度与 MPU6050 姿态传感器节点'
chip_idNoOptional explicit MCU chip model (e.g. 'CH32V003F4P6', 'STM32G030F6P6', 'ATmega328P', 'STM32F103C8T6')
custom_chipNoOptional third-party chip definition with custom pinout, package, and peripheral multiplexing rules
pin_mappingNoOptional custom signal-to-pin allocations, e.g. {'/SCL': 'PC2', '/SDA': 'PC1'}

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changedv0.1.5
    • addedInput schema / properties / chip_id
      Added value: +{
+  "description": "Optional explicit MCU chip model (e.g. 'CH32V003F4P6', 'STM32G030F6P6', 'ATmega328P', 'STM32F103C8T6')",
+  "type": "string"
+}
    • addedInput schema / properties / custom_chip
      Added value: +{
+  "description": "Optional third-party chip definition with custom pinout, package, and peripheral multiplexing rules",
+  "type": "object"
+}
    • addedInput schema / properties / pin_mapping
      Added value: +{
+  "description": "Optional custom signal-to-pin allocations, e.g. {'/SCL': 'PC2', '/SDA': 'PC1'}",
+  "type": "object"
+}
    • changedInput schema / properties / prompt / description
      Previous value: -"Natural language prompt describing the target board and peripherals."New value: +"Natural language circuit description, e.g. '基于 CH32V003 的 AHT20 温湿度与 MPU6050 姿态传感器节点'"
  2. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior; the description's word 'deterministic' usefully corroborates the idempotent hint. Beyond that it only adds the synthesizable scope (chips/peripherals) and does not say whether artifacts are returned inline or written to disk, what format the netlist takes, or any size/complexity limits.

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?

Two sentences, front-loaded with the core purpose before the support lists. The second sentence is a dense enumeration that borders on reference data better served elsewhere (list_supported_chips exists), but it is still compact and scannable.

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 generation tool with four parameters (two of them nested objects), no output schema, and a rich sibling ecosystem, the description names the output only vaguely ('netlist and component modules') without format or structure. Given 100% schema coverage the parameter gap is covered, but the return-value story is thin.

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?

Schema coverage is 100%, so the baseline is 3, and the description goes beyond the schema by enumerating the valid MCU models and peripheral blocks that can be named in the prompt or chip_id, which the schema only illustrates with a few examples. It still says nothing about custom_chip or pin_mapping beyond what the schema already documents.

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 (synthesize) and a concrete deliverable (a deterministic hardware netlist plus component modules) generated from a natural language prompt. This is clearly distinguishable from siblings like validate_netlist or the export_* tools, though the description never names a sibling to sharpen the boundary.

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?

There is no explicit 'use this when...' clause and no named alternative, but the enumerated supported MCUs and peripherals function as implicit preconditions: an agent can infer that prompts targeting unsupported chips will fail. That is enough for implied usage but not for a routed decision against siblings such as list_supported_chips or register_custom_chip.

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