Skip to main content
Glama

breadboardhub circuits

Change a circuit

edit_circuit

Changes a CircuitJS circuit as asked in plain words, such as "make the two resistors parallel", "add a voltmeter across the LED" or "use a 12V supply", or answers a question about it ("what does the 10 mH part do?"). The changed circuit passes breadboardhub's structural checks, with one corrected attempt if needed; a change that would break the circuit is refused and the circuit is returned unchanged. Returns the new circuit, a link that opens it running live, and the parts to buy with supplier links. Takes up to a minute. Counts toward the daily design limit.

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": {
      "circuit": "<circuit>",
      "change": "<change>"
    },
    "name": "edit_circuit"
  }
}

Input Schema

NameRequiredDescriptionDefault
changeYesWhat to change, or a question about the circuit, in plain words (3 to 1,000 characters).
circuitYesThe circuit: a CircuitJS export (a "$" options line, then one part per line, at most 20,000 characters), or a breadboardhub.com/sim link that carries one.
purposeNoOptional: what the circuit is for, in plain words (at most 1,000 characters). Helps keep the change in line with it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4/5.0
Behavior5/5

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

Substantially exceeds the annotations: it discloses a structural-validation gate, exactly one automatic retry, refusal semantics with the circuit returned unchanged on a breaking change, latency expectation ("up to a minute"), and quota consumption against the daily design limit. It also spells out the return payload (new circuit, live-run link, parts list with supplier links), which no output schema provides. Nothing here contradicts readOnlyHint=false or destructiveHint=false — a non-idempotent, non-destructive transform that never leaves a broken circuit matches the stated hints.

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 action and examples, then behavior, then outputs, then cost — a sensible priority order with no filler. It runs to four dense sentences, the longest of which chains validation, retry, and refusal; that clause could be split or trimmed for faster scanning. Nothing is redundant with the schema or annotations.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema, the description correctly shoulders the burden of describing the return value (new circuit, live-run link, purchasable parts with supplier links). It also covers the two operational facts an agent most needs before committing: expected duration and that the call consumes the daily design budget. For a non-idempotent mutation with refusal semantics, this is complete.

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 the schema already documents all three parameters including formats and length bounds; the baseline is therefore 3. The description does add one genuinely useful clarification beyond the schema — that "change" may be a question rather than a mutation instruction — but says nothing further about how "purpose" steers the edit or what the circuit-string forms look like.

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?

Opens with a specific verb+resource ("Changes a CircuitJS circuit") and immediately scopes the input vocabulary with three concrete examples (parallel resistors, add a voltmeter, 12V supply). It also discloses a secondary mode (answering a question about the circuit), which prevents mis-selection for read-like intents. It does not name or contrast any sibling such as design_circuit or simulate_circuit, so the agent must infer the boundary between editing an existing circuit and creating one.

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?

Usage is implied by the examples — pass existing CircuitJS export text plus a plain-language instruction — and the local/remote circuit source is stated. There is no explicit when-not-to-use guidance and no routing statement distinguishing this from design_circuit (create new) or check_circuit (validate only), which is the most likely source of wrong-tool selection here. The refusal behavior is a behavioral rule, not selection guidance.

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