Place window

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

Goes well beyond the annotations: the annotations only say it is a non-destructive, idempotent mutation, while the description adds the reversible-by-repeating nuance ("Not undoable as one step; place it again to change it"), the permission dependency, and the version requirement. The "place it again to change it" note is consistent with, not contrary to, idempotentHint=true.

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?

Effectively one dense paragraph with the core action front-loaded and each following sentence carrying distinct information (Space bound, target window, permission, undo behavior, alternative, version). It reads as slightly run-on, and the version requirement could be deferred, but there is little waste.

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 single-enum-parameter tool with no output schema and full annotation coverage, an agent needs action, target, permission, undo semantics, and sibling routing — all present. The unusual risk of acting on Claude's own window is called out explicitly, which closes the main remaining ambiguity.

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% and the enum itself documents every valid value, so the parameter is already fully specified. The description's grouping of values into half, quarter, maximize, centre and next-display only re-labels what the schema already shows, adding organization but no new semantics.

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 pair ("resize and move") against a specific resource ("the user's frontmost window on its current display") and enumerates the resulting placements. It also explicitly clarifies which window is meant, including the surprising case that from Claude Desktop it is Claude's own window, which no sibling description covers.

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?

Tells the agent when to use this versus a named alternative: "Use move_window_to_space to send a window to another Space instead," and pairs it with "It stays on the same Space" so the Space bound is unambiguous. It also gives the precondition (Accessibility permission already granted) and a version floor (Spacepal 1.2.8+).

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