Skip to main content
Glama
nx-ai-bridge

nx-ai-bridge

by qiuyekai

nx_api_lookup

Search the NX Open .NET API loaded in your running NX to list type members and signatures or find types and members by text before writing journal code.

Instructions

Search the NX Open .NET API that is actually loaded in the running NX (works offline, no docs needed). Give type (e.g. 'NXOpen.Features.ExtrudeBuilder') to list its members with signatures, and/or query to find types/members whose name contains the text. Use before writing run_journal code.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "nx_api_lookup"
  }
}

Input Schema

NameRequiredDescriptionDefault
typeNoFull or short type name to describe.
limitNoMaximum number of results.
queryNoCase-insensitive substring to search for in type and member names.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.2/5.0
Behavior4/5

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

No annotations are supplied, so the description carries the burden, and it does disclose the key behavioral trait: results come from the API actually loaded in the running process, not from static documentation, and it works offline. It implies a read-only reflection lookup without saying so explicitly, and gives no hints on result size beyond the schema's limit.

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

Conciseness5/5

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

Three short sentences, front-loaded with what the tool searches and the offline guarantee, followed by parameter usage and the call-ordering tip. No filler or redundant restatement.

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?

With no output schema and no annotations, the description still conveys the shape of results (member lists with signatures, name matches) and the workflow position before run_journal. Minor gaps remain around behavior with zero arguments or no matches, but nothing essential for calling it is missing.

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 100%, so the schema already documents all three parameters, which sets the baseline at 3. The description adds modest meaning by clarifying that `type` returns members with signatures and that `query` matches against both type and member names, but that largely restates the schema text.

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?

States a specific verb and resource: search the NX Open .NET API actually loaded in the running NX. The parenthetical 'works offline, no docs needed' and the example type name make the scope unambiguous, and it is clearly distinct from modeling siblings like extrude or boolean_unite.

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?

Explicitly routes usage: 'Use before writing run_journal code' names the sibling and the ordering. It also explains the division of labor between `type` (describe a type) and `query` (substring search) and permits combining them with 'and/or'. It stops short of stating when not to use it or what happens with neither parameter, so not a full 5.

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