Skip to main content
Glama
Sign In
Grove

Grove

by sai-softwareforest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grove_work_create

Create a local work item for a project to track a unit of work that should end in a reviewed change; it starts in ready status and never opens GitHub issues or PRs.

Instructions

Create a local work item for a project, starting in status ready. issue_url is stored as plain text for reference and is never fetched or opened. Use to record a unit of work that should end in a reviewed change; Grove tracks it but does not implement it or open a pull request. 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": {
      "project": "<project>",
      "title": "<title>"
    },
    "name": "grove_work_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
planNoOptional plan for the work.
titleYes
projectYesProject name, or its numeric id.
issue_urlNoOptional reference URL; stored, never fetched.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already declare non-read-only, non-destructive and closed-world, but the description adds real context beyond them: the item starts in status ready, issue_url is stored as plain text and never fetched or opened, and nothing is sent to GitHub or any other service. The one gap is what the call returns on success, which is not described and there is no output schema.

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?

Three sentences, front-loaded with the core action and the initial status, then the scope caveat and the local-only guarantee. Slight redundancy in repeating the issue_url 'never fetched' point already present in the schema costs it a point but nothing is 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 4-parameter create tool with annotations and no output schema, the description covers what is created, the starting status, side-effect limits and the local-only guarantee. The only missing piece is the shape of the returned created item, which an agent would have to discover from the response.

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 75%, so the schema already documents project, plan and issue_url, and the description largely restates the issue_url behavior ('stored as plain text for reference and is never fetched or opened'). It adds no meaning for title or plan beyond their schema text, so the baseline of 3 applies.

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 ('Create a local work item for a project') plus the initial state ('starting in status ready'), which immediately separates it from grove_work_get, grove_work_list and grove_work_update. It also bounds the tool's role ('Grove tracks it but does not implement it or open a pull request'), so an agent knows this is bookkeeping, not execution.

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?

'Use to record a unit of work that should end in a reviewed change' gives a clear selection criterion, and the note that Grove does not implement or open PRs implicitly excludes the execution case. It does not name a sibling alternative (e.g. grove_work_update for modifying an existing item), so it stops short of explicit routing.

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