Propose a tidier folder tree

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

Annotations already declare readOnly, non-idempotent, open-world, non-destructive, and the description is consistent with all of them. It adds substantial context annotations cannot carry: which data leaves the system (folder names/descriptions, card names/tags, explicitly not summaries), the non-deterministic plan per call, a few seconds of latency from one time-limited model call, the apply-on-web/undo path, and failure modes when no model is configured. Only the exact result format is left implicit.

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?

Front-loaded with the core action and the no-side-effects guarantee, then routing, then data/latency caveats. Dense but every sentence carries operational content; the only mild redundancy is restating the read-only nature after the opening clause.

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?

With no output schema, the description must describe the return value, and it does: a plan of at most 50 operations of enumerated kinds, each with a reason, plus the safety guarantee that hand-filed cards and user-made folders are never touched. Failure conditions are also covered, so an agent has everything needed to call and interpret it.

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?

Zero parameters, so the baseline is high. The description goes further by explaining why there are none ('it always looks at the whole tree'), which heads off attempts to pass a subtree or filter argument that the schema does not have.

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?

Names a specific action (ask the AI model for a plan to tidy the folder tree) and its scope (whole tree, review-only, nothing changes). It explicitly separates itself from driftnet_create_folder, driftnet_update_folder and driftnet_move_items, so an agent can route correctly without opening any schema.

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?

Gives the trigger ('when the reader asks to reorganise in general') and the exclusion with named alternatives for a single specific change. The alternatives map directly to sibling tool names, so the routing decision is fully specified.

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