Skip to main content
Glama

native_export

Destructive

Draw new native schematics with calibrated symbols, rotation, mirroring, and sheet-bounded routing, then verify topology readback without overwriting an existing project.

Instructions

Draw a NEW native schematic with calibrated symbols, rotation and mirroring. Default auto uses full continuous signal wires and sheet bounds, never silently falls back to labels. The LED example uses an authored parallel-channel plan. Explicit labels and wires modes remain opt-in and are also sheet-bounded. routing=schematic uses exact half-grid trees and audited unconnected crossings; sheet_size sets even grid width/height. Topology readback; never overwrites a project.

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": {
      "project": "<project>"
    },
    "name": "native_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
layoutNo
projectYes
routingNo
wire_planNoOrdered explicit orthogonal channels: junctions (@id -> half-grid pair), terminals (@id -> {net:VCC/GND,at:pair,label:optional layout}), wires ({net,ends:[pin or @id,pin or @id],points:[pairs]}), labels (net -> pair or layout), component_labels (component ref -> {ref:layout,value:layout}). Layout permits at (half-grid pair), height/width (0.4..4 grid), rotation (0/90/180/270), visible (boolean). Hiding preserves label/net identity, including supply terminals. All physical nets must still match the circuit model.
placementsNo
sheet_sizeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.8/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=false and destructiveHint=true, so the description's job is to add context, and it does add some: sheet-bounded output, no silent fallback to labels, 'audited unconnected crossings,' and 'Topology readback.' It stops short of saying what file is written, where, or whether existing artifacts are replaced, and 'never overwrites a project' sits in tension with destructiveHint=true without resolving which resources are actually at risk.

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

Conciseness2/5

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

The first sentence is well-formed and front-loaded, but the remainder is a run of dense, jargon-heavy clauses ('audited unconnected crossings,' 'half-grid trees') crammed into few sentences. The LED-example sentence and the trailing 'Topology readback; never overwrites a project' fragment read as leftover notes that do not earn their space in a tool description.

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

Completeness1/5

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

This is a destructive, six-parameter tool with a nested wire_plan object and no output schema, so the description carries a heavy burden. It never states where output is written, what 'Topology readback' actually returns, how the required project argument is interpreted, or what layout='model' vs 'auto' does — leaving major decisions to guesswork.

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

Parameters2/5

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

Schema description coverage is only 17%, so the description must compensate, and it does so only partially. It explains routing='schematic' semantics and that 'sheet_size sets even grid width/height,' but 'layout' (auto vs model), 'placements', and the required 'project' parameter are never addressed, and 'wire_plan' is only gestured at as 'an authored parallel-channel plan' despite being a nested object with its own sub-fields.

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?

The opening sentence states a concrete verb and resource: 'Draw a NEW native schematic with calibrated symbols, rotation and mirroring,' which is enough to know this produces a schematic artifact. It does not, however, distinguish itself from siblings such as native_create, native_preview, or export_svg, and the name 'native_export' sits awkwardly against a verb ('Draw') that implies creation rather than export.

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?

Mode guidance is partially present: 'Default auto uses full continuous signal wires... Explicit labels and wires modes remain opt-in,' which tells the agent the default and that other routing modes are opt-in. There is no guidance on when to choose this tool over native_create/native_preview/export_svg, no prerequisites, and the sentence about the LED example is context about a different artifact rather than a usage rule.

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