Skip to main content
Glama
Trestle MCP

Trestle MCP

Official

Initialize Trestle Workspace

trestle_init
Destructive

Initialize a directory as a Trestle workspace, creating the directory structure and configuration for OSCAL model management. Avoid reinitializing; it overwrites existing task config.

Instructions

Initialize a trestle working directory.

This tool initializes the current directory as a Trestle workspace, creating the necessary directory structure for OSCAL model management.

Do not run this on a workspace that is already initialized. Creating the directories is harmless -- they are only made when missing -- but local and full mode also copy trestle's stock .trestle/config.ini over whatever is there, with no check and no warning, and still report success. That file is where trestle task reads its [task.*] sections from, so an operator's task configuration is gone. Check for a .trestle directory before calling this; there is nothing to gain by running it again.

OSCAL Model Types supported:

  • Catalog

  • Profile

  • Component Definition

  • System Security Plan (SSP)

  • Assessment Plan

  • Assessment Result

  • Plan of Action and Milestones (POAM)

Args: params (TrestleInitInput): Validated input parameters containing: - mode (InitMode): Initialization mode (local/full/govdocs, default: local) - trestle_root (Optional[str]): Path to trestle root directory - verbose (bool): Display verbose output (default: false)

Returns: str: Success message or error details

Examples: - Use when: "Initialize trestle workspace" - Use when: "Set up trestle in full mode" - Don't use when: Workspace is already initialized — this overwrites .trestle/config.ini rather than leaving it alone.

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": {
      "params": "<params>"
    },
    "name": "trestle_init"
  }
}

Input Schema

NameRequiredDescriptionDefault
paramsYes

Output Schema

NameRequiredDescriptionDefault
resultYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.2

TDQS

A4.5/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=false; the description goes well beyond them by pinpointing exactly what is destroyed (.trestle/config.ini, and with it an operator's [task.*] sections), that local and full modes do this with no check and no warning, and that the call still reports success. It also notes the partial safety property (directories only created when missing), which prevents the agent from assuming a fully idempotent no-op. No contradiction with the annotations.

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-loads the destructive warning ahead of the mechanics, which is the right ordering for a hazardous tool, and each paragraph has a job. It is slightly longer than needed: the overwrite risk is stated twice (once in the prose, once in the closing 'Don't use when'), and the enumerated OSCAL model types list adds bulk without helping an agent decide whether to call init.

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?

An output schema exists, so the return contract is already covered and the description's brief 'Returns: str' is harmless. For a single-parameter but destructive setup tool, the risk profile and precondition are complete; the only real hole is undefined behavior for the 'govdocs' mode, which an agent could select from the enum with no idea what it does.

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 reported as 0%, so the description has to carry the parameters, and it does list mode (local/full/govdocs, default local), trestle_root, and verbose. However it only adds real meaning for two of the three modes — local and full are explained as copying config.ini, while what govdocs does is never stated, and verbose/trestle_root get nothing beyond restating the schema. Partial compensation for a coverage gap, so a mid score.

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 ('Initialize a trestle working directory') and immediately clarifies the scope: creating the directory structure for OSCAL model management. The sibling set (author_*, import, validate) are all downstream operations, so an agent can tell this is the one-time setup step without inspecting any schema.

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

Usage Guidelines5/5

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

Gives explicit when-to-use examples ('Initialize trestle workspace', 'Set up trestle in full mode') and a hard exclusion with a concrete precondition check: 'Check for a .trestle directory before calling this'. The 'Don't use when' clause is tied to a specific failure mode rather than generic caution.

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