things_move_item

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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=true) by disclosing specific behaviors: requires the latest revision and write permission, moving projects can affect descendants, and what it does NOT do (reorder items, address headings, or restore Trash). No contradiction with annotations; it enriches them with concurrency, authorization, and side-effect detail.

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?

Four dense sentences, each earning its place: the first fronts the core action and destinations, the next two state hard constraints, and the last covers requirements and negative scope. No fluff or repetition.

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?

For a complex tool with 4 required params, nested oneOf destinations, and zero schema descriptions, the description fully specifies the move matrix (valid and invalid), side effects, prerequisites, and exclusions. Since an output schema exists, return-value coverage is not needed.

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?

With schema description coverage at 0%, the description carries the burden and largely delivers: it explains the destination parameter's valid values (project, area, Inbox Today Anytime Someday, detach) and clarifies valid kind/destination combinations. It also gives expectedRevision meaning ('requires the latest revision'). Only requestId semantics are left to the schema/format, a minor gap.

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?

States a specific verb ('Move') with the resource (to-do/project) and enumerates the valid moves: to-do to project/area/list, project to area, detaching a parent. This is concrete and semantically distinct from siblings like things_trash_item (trash), things_schedule_item (scheduling), and things_update_item (updates).

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?

The description implies usage context through explicit constraints ('Projects support Today and Someday', 'Project Anytime and direct Logbook moves are unavailable'), which tells an agent what operations are possible. However, it never names alternative tools or states when-not-to-use this tool in favor of a sibling, leaving routing decisions to inference.

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