Skip to main content
Glama

manufacturing_bom

Destructive

Export an audited UTF-8 CSV and JSON assembly BOM from a saved, DSN/CDB-consistent native project, counting each physical package once and listing unassigned packages separately.

Instructions

Export an audited UTF-8 CSV and JSON assembly BOM from a SAVED, DSN/CDB-consistent native project. Requires input SHA-256, counts each physical package once across units, reports unassigned packages separately, escapes CSV formulas, writes NEW workspace output only. Not unsaved-session data, Gerber/Excellon, verified PCB population or fabrication certification.

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": {
      "path": "<path>",
      "expected_sha256": "<expected_sha256>"
    },
    "name": "manufacturing_bom"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
expected_sha256Yes

Schema Changelog

Changes observed during successful MCP inspections.

  1. 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 readOnlyHint=false, destructiveHint=true, and openWorldHint=false. The description adds behavioral context (counts each physical package once, reports unassigned packages separately, escapes CSV formulas, requires SHA-256, writes NEW workspace output only), but it does not clarify what gets destroyed given destructiveHint=true, and the phrase 'writes NEW workspace output only' is ambiguous about overwriting existing files.

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?

The description is front-loaded with the core action and its main constraints, followed by a concise set of exclusions. It is dense but every sentence adds value, with no redundant or filler wording.

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 tool with no output schema, the description covers purpose, prerequisites, behavioral rules, and exclusions well enough to call it correctly. Minor gaps remain: it does not specify the output file location, naming convention, or behavior on hash mismatch, but these are not critical to basic invocation.

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 0%, so the description must supply parameter meaning. It explains expected_sha256 as an 'input SHA-256' and implies path points to a SAVED, DSN/CDB-consistent native project. However, it does not define the SHA-256 format, explain what DSN/CDB-consistent means, or state how the path is structured, leaving some ambiguity.

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 description states a specific verb ('Export') and resource ('assembly BOM') with output formats (UTF-8 CSV and JSON) and source constraints (SAVED, DSN/CDB-consistent native project). It distinguishes the tool from outputs like Gerber/Excellon and fabrication certification, but does not name any sibling tool, so sibling differentiation is implied rather than explicit.

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?

The description implies when to use it by requiring a SAVED, DSN/CDB-consistent native project and explicitly excludes unsaved-session data, Gerber/Excellon, verified PCB population, and fabrication certification. However, it does not name alternatives (e.g., native_export, export_netlist) or specify when to choose this over them, leaving usage guidance inferred rather than explicit.

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