Skip to main content
Glama

add_pour

Add a copper pour for a selected net on one PCB layer, filling around other nets and counting joined copper as routed. Returns the pour ID and connected pads for verification.

Instructions

Add a copper pour of a net on one layer as ONE change; it fills round other nets' copper on every build, and what it joins counts as routed. The answer gives its id and the pads it joins: check them.

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>",
      "net": "<net>",
      "layer": "<layer>"
    },
    "name": "add_pour"
  }
}

Input Schema

NameRequiredDescriptionDefault
netYesNet name, e.g. "GND"
fileYesCircuit file
layerYesinner1, inner2 only on 4 layers
propsNo
outlineNoDefault the whole board

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With no annotations available, the description carries the full burden and does add real behavioral value: it discloses that the pour refills around other nets' copper on every build (a re-pour/rebuild interaction), that joined copper counts as routed connectivity, that it is applied as a single atomic change, and that the response contains an id plus pads to verify. It omits what could be destroyed or invalidated (e.g., clearance/DRC impact, whether an existing pour is replaced) and permission requirements, leaving meaningful gaps for an unannotated mutation tool.

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 dense sentences, front-loaded with the action and its build-time consequence. Every clause carries information, though the phrasing ('as ONE change', 'check them') is terse enough to be slightly ambiguous.

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 a 5-parameter mutation tool with no output schema, the description covers the action, side effects on other copper, connectivity semantics, and what the response returns. Only the tuning props and outline override behavior are left unexplained, and those are largely covered by the schema.

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 coverage is high (80%), with net, layer enum, and outline already described, so the schema does the heavy lifting. The prose restates 'net' and 'one layer' but adds nothing about the undocumented props object (thermal, thermalGap, minWidth, clearance, priority) or when to supply a custom outline versus the default whole board.

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 concrete verb and resource — 'Add a copper pour of a net on one layer' — which an agent can clearly distinguish from add_trace, add_via, or add_hole by object type. It stops short of naming a sibling alternative, so no explicit differentiation is made.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explains consequences ('fills round other nets' copper', 'what it joins counts as routed') but gives no when-to-use guidance versus alternatives such as routing a trace or editing copper manually, and no prerequisites for calling it.

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