Skip to main content
Glama
pcb-agent-mcp

pcb-agent-mcp

board_apply

Applies a prepared PCB change plan to a board, with dry-run, in-place or new-file output, and DRC safety gates to control risky edits.

Instructions

...

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": {
      "plan_id": "<plan_id>"
    },
    "name": "board_apply"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNo ...
optionsNo
plan_idYes ...

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.43

TDQS

D1/5.0
Behavior1/5

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

No annotations are provided, so the description carries the full behavioral burden and delivers nothing. The schema hints at consequential behavior (a confirm flag, dry_run, opt-in flags for allow_new_violations, allow_layer_changes, allow_plane_crossing), but the description never explains that this mutates the board, what gets changed or destroyed, or what confirm/dry_run actually do.

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

Conciseness1/5

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

There is no content to be concise about; an empty string is under-specification, not conciseness. Nothing is front-loaded because nothing is stated.

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 mutating, high-stakes tool with a nested options object, multiple permissive allow_* flags, no annotations, and no output schema. A non-empty description is essential at this complexity level, and it is entirely missing.

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

Parameters1/5

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

Schema description coverage is nominally 67%, but every property description is also a ' ...' placeholder, so the structured fields convey names only. Nothing explains plan_id's provenance, what confirm authorizes, or how the nested options gate destructive outcomes — the most safety-critical parameter semantics are entirely absent.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose1/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description is literally an empty placeholder (' ...'), so it states neither a verb nor a resource. From the name and schema an agent might guess this applies a saved plan, but the definition itself supplies no purpose statement and does nothing to distinguish board_apply from siblings like board_propose or schematic_apply.

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

Usage Guidelines1/5

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

No when-to-use guidance, no prerequisites, and no mention of alternatives. With siblings such as board_propose, board_create, and board_drc present, there is no way to know from this definition when applying a plan is the correct action versus proposing one first.

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