Skip to main content
Glama
Sign In
Grove

Grove

by sai-softwareforest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grove_project_create

Registers a codebase as a Grove project by mapping a unique name to its root directory, so you can scan it next; writes only a local database row and leaves files untouched.

Instructions

Register a codebase as a Grove project: a unique name plus the root directory to map. Use once per codebase, before grove_scan. Only a row in Grove's own database is written; the directory itself is not touched. Grove is local only: scans are read-only and nothing is sent to GitHub or any other service.

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>",
      "root_path": "<root_path>"
    },
    "name": "grove_project_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesUnique project name: letters, digits, '.', '_' or '-'.
root_pathYesExisting directory holding the codebase.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.5/5.0
Behavior5/5

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

Annotations declare readOnlyHint=false, destructiveHint=false and openWorldHint=false, and the description explains exactly why: only a row in Grove's own database is written and the directory itself is not touched. It also discloses the local-only/no-external-service boundary, which is behavior an agent cannot infer from the structured fields. Nothing here contradicts 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.

Conciseness5/5

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

Three sentences, front-loaded with purpose, then ordering, then side effects and trust boundary. Every sentence carries distinct information and none restates the tool name.

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

Completeness5/5

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

For a two-parameter creation tool with no output schema, the description covers what is created, when to call it relative to grove_scan, what is and isn't mutated, and the local-only guarantee. An agent has everything needed to invoke it correctly.

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 100%, so both parameters are already documented (unique name character rules, existing directory). The description's 'unique name plus the root directory to map' adds only the framing that the path gets mapped rather than mutated. Baseline 3 is appropriate when the schema carries the detail.

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 ('Register a codebase as a Grove project') and immediately pins the scope to a unique name plus a root directory to map. That distinguishes it cleanly from grove_project_get/list and grove_scan without needing to inspect schemas.

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 timing and cardinality guidance — 'use once per codebase, before grove_scan' — which tells the agent both the prerequisite ordering and that it is not idempotently re-callable per codebase. It stops short of naming a negative case (e.g., what to do if the project already exists), 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.

Deploy Server

Other Tools