Skip to main content
Glama

create_part

Build a library part from a datasheet: numbered pins with names/types, package string or custom footprint from land-pattern pads, MPN and suppliers. Existing IDs need replace.

Instructions

Create a library part from a datasheet you have read: pins by number with names and types, a footprint string (sot23_5, 0402), MPN, suppliers. When no string fits, package { "file": "footprint.yaml" } with footprint_file pads copied from the datasheet land pattern (never estimated). datasheet (url, file, title) e.g. { "url": "https://example.com/ds.pdf", "title": "TJA1051 datasheet" }; pin table pages go to attach_datasheet. An existing id is refused unless replace. The part starts NOT verified: tell the human to check verification.md.

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": {
      "id": "<id>",
      "title": "<title>",
      "package": "<package>",
      "pins": "<pins>"
    },
    "name": "create_part"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYese.g. AP2112K-3.3
mpnNoFull orderable number
pinsYese.g. { "1": { "name": "VIN", "type": "power_in" } }, or text, "1 VIN power_in" per line. A repeated name (a tab) is addressed as pin<n>
modelNoFor simulate (guide { topic: "modules" })
titleYes
packageYese.g. sot23_5, soic8, or { "file": "footprint.yaml" }
replaceNo
datasheetNoOnly url, file, title
suppliersNoe.g. { "lcsc": "C51118" }
descriptionNo
manufacturerNo
footprint_fileNoPads in mm, y up, origin at the centre

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.3/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does a lot: it discloses the id-conflict rule (refused unless replace), the post-creation state ('starts NOT verified: tell the human to check verification.md'), and a data-integrity constraint ('pads copied from the datasheet land pattern (never estimated)'). It stops short of saying where the part is persisted or what a failure response looks like.

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 core action and free of filler, but the telegraphic semicolon-chained fragments and inline JSON blobs make it harder to scan than it needs to be. Every clause does carry information, so nothing is genuinely wasted.

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 12-parameter, deeply nested, annotation-free, output-schema-free creation tool, the description covers the main flow, the two conditional paths, and the conflict/verification lifecycle. The remaining gap is the unmentioned model parameter and persistence semantics, both partly mitigated by schema descriptions.

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

Parameters4/5

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

Adds real meaning beyond the 67%-covered schema: the text alternative for pins ('1 VIN power_in' per line), the repeated-name/tab addressing rule, the string-vs-file package fork, and a concrete datasheet example. It leaves several parameters (model, manufacturer, description, footprint_file body/courtyard/silkscreen) to the schema alone.

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

Purpose5/5

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

Opens with a specific verb and resource ('Create a library part from a datasheet you have read') and immediately enumerates the payload shape (pins by number, footprint string, MPN, suppliers). That distinguishes it from import_part and attach_datasheet, which handle pre-existing data and raw datasheet pages respectively.

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

Usage Guidelines4/5

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

Gives explicit routing ('pin table pages go to attach_datasheet') and conditional branches ('When no string fits, package { "file": "footprint.yaml" }', 'An existing id is refused unless replace'). It does not explicitly contrast against import_part or set_part_fields, but the 'from a datasheet you have read' framing implies the create-from-scratch case.

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