Skip to main content
Glama
Sign In
Grove

Grove

by sai-softwareforest
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

grove_knowledge_write

Save lasting decisions, conventions, or lessons under stable slug keys, preserving revisions and optionally scoping notes to a project for later sessions.

Instructions

Save a lasting note (a decision, a convention, a lesson) under a stable slug key. Writing an existing key adds a new revision; earlier revisions are kept and never overwritten. Give a project to scope the note to it, or omit project for a workspace-level note. Use for knowledge worth finding again in later sessions, not for scratch notes. 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": {
      "key": "<key>",
      "title": "<title>",
      "body": "<body>"
    },
    "name": "grove_knowledge_write"
  }
}

Input Schema

NameRequiredDescriptionDefault
keyYesStable slug: lower-case letters, digits, '.', '_' or '-'.
bodyYesThe note itself, usually markdown.
titleYes
projectNoProject name or id. Omit for a workspace-level note.

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 only declare non-read-only, non-destructive, closed-world; the description adds substantive behavior: existing keys append a new revision, earlier revisions are never overwritten, and nothing leaves the local Grove store. That revision-accumulation semantics is the single most important thing an agent needs to know before writing, and it is not in 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?

Four tight sentences, front-loaded with the write action and revision semantics before scoping and usage boundaries. Every sentence carries distinct information; the closing local-only sentence is slightly redundant with openWorldHint but reinforces it usefully.

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 mutation tool with no output schema, it covers purpose, scoping, revision persistence, and side-effect scope. The only gap is what a successful write returns (e.g., revision identifier), which an agent might want in order to chain follow-up calls.

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 key format, body, and the project-omission case; the description largely restates the project scoping rule. It does add meaning for key by explaining that the slug is stable across revisions and that a repeat write appends rather than replaces, which the schema does not convey.

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 (save) and resource (a lasting note: decision, convention, lesson) keyed by a stable slug, which cleanly separates it from the read-oriented siblings grove_knowledge_get and grove_knowledge_search. The examples of note types and the revision framing make the 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?

Explicitly says when to use it (knowledge worth finding again in later sessions) and when not (scratch notes), plus how to choose scoping via project or omission. It does not name a sibling alternative, but the when-not guidance is a real usage boundary rather than a vague implication.

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