gardener_split

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

Annotations provide minimal info (readOnlyHint=false, destructiveHint=false). Description fully compensates: explains it only creates reviewable proposals (not actual changes), details output structure (one 'split' setup proposal plus one 'reproject' per memory under plan 'split-<source>'), and notes it never creates or moves memories directly. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is front-loaded with purpose and usage. All sentences contribute meaningful information, though length could be slightly tighter. No redundancy or fluff.

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

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

Covers prerequisites (LLM chat client, known slug), explains output structure in lieu of output schema, and differentiates from multiple sibling tools. No gaps identified for a planning-level tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so baseline is 3. Description adds value by reiterating that 'source' is a project slug and linking to project_list for discovery, and that 'instruction' is optional for guiding children/shared parent. This provides context beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Description uses a specific verb ('divide') and resource ('project split'), clearly distinguishes from siblings like project_create and gardener_proposals, and gives a concrete example. It explicitly states the tool does not create or move projects/memories, only pending proposals.

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

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

Explicitly states when to use ('break one project into several'), mentions that gardener_request routes here via splitSource, and provides a clear workflow: propose via this tool, review with gardener_proposals, apply with gardener_apply. It also clarifies prerequisites (LLM chat client, known source slug).

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