Skip to main content
Glama

gardener_split

Plan splitting one existing project into multiple child projects with a shared parent. Generates reviewable proposals only, creating or moving nothing.

Instructions

Plan a project SPLIT: divide one existing project into two or more NEW child projects, keeping cross-platform memories in a shared parent (e.g. split example-app into example-ios + example-android with shared example-mobile-apps). Use this when the user wants to break one project into several -- gardener_request points you here (via splitSource) when it detects that intent. It NEVER creates a project or moves a memory: it only creates reviewable pending proposals -- one 'split' setup proposal plus one 'reproject' per memory, all under plan 'split-'. Review with gardener_proposals, then apply each with gardener_apply (or retarget a memory first in the console). Needs an LLM chat client and a known source project slug (see project_list).

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": {
      "source": "<source>"
    },
    "name": "gardener_split"
  }
}

Input Schema

NameRequiredDescriptionDefault
sourceYesthe project slug to split (its own memories are classified into the children/shared parent)
sessionNothe session to act as: the name session_start returned, the cc/<id> or cx/<id> on your briefing's 'Seam session' line, or a session ULID. It scopes and credits this call. Defaults to this connection's session; pass it on every call when session_start reports the connection as stateless
instructionNooptional guidance: which children, what stays shared

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.4
    • addedInput schema / properties / session
      Added value: +{
      +  "description": "the session to act as: the name session_start returned, the cc/<id> or cx/<id> on your briefing's 'Seam session' line, or a session ULID. It scopes and credits this call. Defaults to this connection's session; pass it on every call when session_start reports the connection as stateless",
      +  "type": "string"
      +}
  2. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Though annotations already say readOnlyHint=false and destructiveHint=false, the description adds the key clarification that it NEVER creates a project or moves a memory and only produces reviewable pending proposals. It additionally names the shape of the output (one 'split' setup proposal plus one 'reproject' per memory), states a deterministic plan name 'split-<source>', and notes the LLM chat client dependency, all of which go well beyond what the annotations convey.

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?

The description is a single front-loaded block that leads with the core action and example before routing and workflow details. It is a bit dense, but every sentence carries weight and no line is redundant.

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 three-parameter planning tool with no output schema, the description supplies the missing pieces an agent needs: prerequisites (LLM chat client, known source project slug), what is produced (pending proposals under a named plan), and the follow-up path for review and application. Nothing required to invoke it correctly is absent.

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 the input schema already documents source, session, and instruction, meaning the baseline is 3. The description reinforces source with 'a known source project slug (see project_list)' and mentions the optional instruction is for naming which children and what stays shared, but that largely echoes the schema rather than adding new syntax or format 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?

The description uses a specific verb and resource ('Plan a project SPLIT: divide one existing project into two or more NEW child projects') and immediately grounds it with a concrete example (example-app into example-ios + example-android with shared example-mobile-apps). It also draws a firm line from siblings like gardener_request and gardener_proposals, so the agent can distinguish this tool from its neighbors without opening a 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?

Explicit selection guidance is present: 'Use this when the user wants to break one project into several,' plus the note that gardener_request routes here via splitSource when it detects that intent. The description also closes the loop on the workflow, telling the agent to review with gardener_proposals and then apply with gardener_apply, so the user knows exactly which neighboring tool comes next.

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