FTC Toolchain

by Sanjit-K

Overview Schema Source Related Servers Discussions Admin

TypeScript

Local

Create a calculation helper

create_calculation

Scaffold a stateless helper class to centralize math calculations, removing logic from OpMode and subsystem files.

Instructions

Scaffold a stateless static-only helper class (e.g. live trajectory math) that any OpMode or subsystem can call. Keeps math out of subsystem/OpMode files.

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": {
      "name": "<name>"
    },
    "name": "create_calculation"
  }
}

Input Schema

Name	Required	Description
`name`	Yes	Class name, e.g. TrajectorySolver
`group`	No	Package group (default: util)
`dryRun`	No	Validate and return the generated Java without writing any files
`overwrite`	No
`description`	No
`projectPath`	No	Path to the FtcRobotController SDK project. Defaults to $FTC_TOOLCHAIN_PROJECT_DIR, then the workspace clone made by create_project.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.2.0Jul 13, 2026

TDQS

A3.6/5.0

Behavior2/5

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

No annotations present, so description carries full burden. It only says 'scaffold a stateless static-only helper class' but doesn't disclose side effects like file creation, overwrite behavior, or prerequisites (e.g., existing project). The dryRun and overwrite parameters hint at behavior but description ignores them.

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?

Two sentences, highly efficient. Every word adds value—'stateless static-only' clarifies constraints, 'live trajectory math' gives example. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Tool has 6 parameters, no output schema, no annotations. Description omits how the scaffolding works (e.g., file creation, package structure), doesn't explain parameter roles, and provides no return value info. Incomplete for an agent to use reliably without external knowledge.

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 covers 67% of parameters with descriptions (name, group, dryRun, projectPath). Description adds no extra meaning to parameters beyond what schema provides. Baseline is 3 due to moderate schema coverage, but description does not compensate for the missing 33%.

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?

Description clearly states the tool scaffolds a stateless static-only helper class for calculations, distinguishing it from sibling tools like create_opmode and create_subsystem. Specific verb 'scaffold' and phrase 'keeps math out of subsystem/OpMode files' make purpose unambiguous.

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?

Implied usage: when needing a helper class for stateless math callable by OpModes/subsystems. Sibling tools provide contrast (e.g., create_opmode for OpModes, create_subsystem for subsystems), so context is clear, but no explicit when-not or alternative mentioned.

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